ci(coverage): add v8 coverage with 80% thresholds and fix prettier ignores#507
Merged
JustAGhosT merged 100 commits intomainfrom Apr 1, 2026
Merged
ci(coverage): add v8 coverage with 80% thresholds and fix prettier ignores#507JustAGhosT merged 100 commits intomainfrom
JustAGhosT merged 100 commits intomainfrom
Conversation
* fix(commands): add AskUserQuestion to VALID_TOOLS and /start command The /start command session got stuck because AskUserQuestion was not included in the allowed-tools whitelist. This fix addresses three issues: 1. VALID_TOOLS in spec-validator was missing AskUserQuestion, TodoWrite, Agent, and NotebookEdit — preventing commands from declaring these Claude Code built-in tools in their allowed-tools. 2. The /start command template now explicitly includes AskUserQuestion in its allowed-tools frontmatter and instructs the agent to use it for interactive guided choices (Phase 3). 3. Added /start command spec to commands.yaml with AskUserQuestion as a declared tool dependency. Also adds a test case validating all four newly-added tools are accepted by the spec validator. https://claude.ai/code/session_01Qh3Xk3jFkVdeRAXTqLvq3M * fix(commands): remove unrendered Handlebars comment from start.md output The generated .claude/commands/start.md contained a raw {{! ... }} Handlebars comment that was not processed by the sync engine. Remove it so the generated output is clean Markdown. https://claude.ai/code/session_01Qh3Xk3jFkVdeRAXTqLvq3M --------- Co-authored-by: Claude <noreply@anthropic.com>
* feat(sync): add configurable command prefix for generated slash commands Add `commandPrefix` setting to overlay settings that namespaces all generated slash commands across platforms: - Claude Code: subdirectory strategy (kits/check.md → /project:kits:check) - Cursor/Windsurf/Copilot/Codex: filename prefix (kits-check.md → /kits-check) - Team commands excluded from prefixing (already namespaced) Changes: - Add resolveCommandPath() helper with subdirectory/filename strategies - Update syncClaudeCommands, syncClaudeSkills, syncCursorCommands, syncWindsurfCommands, syncCopilotPrompts, syncCodexSkills - Add commandPrefix to vars from overlay settings - Add commandPrefixedName to buildCommandVars - Add 16 unit + integration tests (all pass, 93 existing tests unaffected) Default is null (no prefix) for full backwards compatibility. https://claude.ai/code/session_01EBjmVEhi7fP2huAL3SBR6p * fix(sync): address review findings for command prefix - Remove unused afterAll import from test file - Add clarifying comment that non-spec command files are also prefixed - Add 2 integration tests verifying commandPrefixedName template variable renders correctly with and without prefix https://claude.ai/code/session_01EBjmVEhi7fP2huAL3SBR6p --------- Co-authored-by: Claude <noreply@anthropic.com>
…ility (#390) * fix(ci): resolve 7 bugs from project review - BUG-001: Replace flaky discover test with controlled temp fixture - BUG-002: Run prettier --write to fix formatting drift - BUG-003: Add form-template detection skip in issue label validation - BUG-005: Change claude.yml to self-hosted runner - BUG-006: Align branch protection required status checks with project.yaml - BUG-007: Fix command injection in resolve-merge.sh (use grep -F) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * docs: update changelog, add planning registry review findings - Add changelog entries for Wave 1-3 fixes (Added/Changed/Fixed/Removed) - Add Project Review Findings section to planning registry (PR-001 to PR-014) - Update planning docs after sync merge Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(review): add --generate-plans flag to project-review command Add Phase 2.5 plan generation after project review findings. When --generate-plans is passed (default: true), scaffold plan files from critical/high findings into docs/planning/review-findings/. Also includes sync cleanup of stale cursor/windsurf settings. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore(sync): regenerate all outputs after project review fixes Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(cli): dynamic flag loading from commands.yaml + context-aware template hook - Replace ~200 lines of hardcoded VALID_FLAGS/FLAG_TYPES with loadCommandFlags() that reads flag definitions from commands.yaml at startup - CLI_INTERNAL_FLAGS/CLI_INTERNAL_FLAG_TYPES cover commands not in commands.yaml - Self-validation warns at startup if any flag is missing a type definition - Update cli.test.mjs to validate CLI_INTERNAL_FLAGS consistency - Fix scaffold-once orphan bug: carry forward manifest entries for files skipped by scaffold-once so orphan cleanup does not delete them - Make protect-templates hook context-aware: skip protection in the agentkit-forge source repo (detected via package.json name) so maintainer agents can edit templates; block only in downstream repos Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(sync): add managed-mode script templates for downstream repos Add 14 script templates (.agentkit/templates/scripts/) with `managed` scaffold mode so downstream repos receive script updates via three-way merge while preserving local customizations. Templates include: create-doc, update-changelog, validate-documentation, validate-numbering, check-documentation-requirement, sync-issues, sync-split-pr, setup-agentkit-branch-governance, and resolve-merge (both .sh and .ps1 variants where applicable). Parameterized templates use {{defaultBranch}} and branch protection variables from project.yaml. Engine wired via syncScripts() under doc-scaffolding feature gate. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(teams): add TeamForge meta-team for agent team creation (cogmesh #130) Add the TEAMFORGE meta-team (T11) — a structured pipeline for creating, validating, and deploying new agent team specifications. Adapted from cogmesh #130 with a simplified 6-agent pipeline: - input-clarifier: assess requests, extract constraints - mission-definer: lock team definition (ID, scope, accepts) - role-architect: design agent roles and dependencies - prompt-engineer: write agent descriptions and rules - flow-designer: design team command and integration points - team-validator: quality gate for spec consistency Includes /team-forge command with --task flag (create-team, validate-team, audit-teams, update-team) and planning doc. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(teams): add Strategic Ops team for cross-project coordination Add the STRATEGIC OPS team (T12) — handles framework governance, portfolio analysis, adoption strategy, impact assessment, and release coordination across all repos using AgentKit Forge. 5-agent pipeline: - portfolio-analyst: inventory repos, detect drift, adoption metrics - governance-advisor: versioning strategy, breaking change protocols - adoption-strategist: onboarding, migration paths, rollout plans - impact-assessor: blast radius analysis for template/spec changes - release-coordinator: version bumps, sync waves, release comms Includes /team-strategic-ops command with --task and --scope flags. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(agents): add agent/team relationship matrix analysis engine + scripts Add comprehensive agent/team relationship analysis with 8 cross-reference matrices and 10 supplementary analyses (orphans, cycles, bottlenecks, reachability, critical path, notification amplifiers, etc.). - Fix YAML structure: strategic-ops agents now under own top-level key - Add explicit agents: lists to forge + strategic-ops teams in teams.yaml - Add consolidation detection responsibilities to portfolio-analyst - Create agent-analysis.mjs engine module (loadFullAgentGraph + renderers) - Wire analyze-agents CLI command with --output/--matrix/--format flags - Add managed-scaffold script templates (bash + PowerShell) - Integrate into sync pipeline (auto-regenerates matrix on spec changes) - Add 33 tests covering all matrices, analyses, and edge cases Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: update documentation files and add plan template - Add trailing newlines to Cursor command documentation files for consistency - Add new plan template files for project planning - Improve markdown table formatting in Claude skills documentation - Remove obsolete .clinerules/testing.md file - Update various rule files with better formatting and advisory rule alignment * feat(agents): add spec-compliance-auditor feedback loop + Cost Ops team (T14) - Add spec-compliance-auditor to operations category (quality team) — closes the feedback loop between agent specs and actual behavior - Add Cost Ops team (T14) with 5 agents: model-economist, token-efficiency-engineer, vendor-arbitrage-analyst, grant-hunter, cost-ops-monitor - Add ai-cost-ops rules domain with 6 conventions (model routing, token budgets, caching, batch APIs, vendor abstraction, credit tracking) - Add team-cost-ops command with --task, --period, --provider flags - Update notification chains: data→cost-ops-monitor, infra→model-economist, retrospective-analyst→spec-compliance-auditor - Add intake routes: cost-ops, agent-performance Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(teams): add implement to cost-ops team accepts list Resolves agent/team accepts mismatch — token-efficiency-engineer accepts implement but the team definition only had investigate/review/plan/document. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(cost-ops): add multi-provider infra cost ticket to backlog Add detailed planning ticket for multi-provider infrastructure cost normalisation, routing, and cost-agent integration. Covers 9 providers (Anthropic, OpenAI, Google, Mistral, Cohere, self-hosted, Azure, AWS, GCP) with 3-phase delivery plan and cross-team dependency tracking. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(templates): resolve PR review comments from CodeRabbit - Fix protect-templates.sh: package name check uses correct "agentkit-forge-runtime" instead of "agentkit-forge" - Fix protect-templates.ps1: malformed path (missing separator before .agentkit) and same package name correction - Fix update-changelog.ps1: change .mjs to .cjs to match CommonJS require() syntax used in the inline Node script - Fix resolve-merge.sh: add fallback for {{defaultBranch}} placeholder - Fix AGENT_TEAMS.md: resolve three-way merge conflict markers left by sync engine, keeping user formatting + implement in cost-ops Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(cost-ops): add WebSearch/WebFetch tools to cost-ops agents Enable web research capabilities for cost-ops team: - Add WebSearch and WebFetch to /team-cost-ops allowed-tools - Add WebSearch and WebFetch to model-economist, vendor-arbitrage-analyst, and grant-hunter agent preferred-tools - Add web intake expansion ticket (P2) for MCP crawler, Puppeteer integration, automated pricing refresh, and cross-session persistence - Regenerate sync outputs Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(cost-ops): add Cost Ops team, agents, and multi-provider cost ticket (#364) * feat(agents): add spec-compliance-auditor feedback loop + Cost Ops team (T14) - Add spec-compliance-auditor to operations category (quality team) — closes the feedback loop between agent specs and actual behavior - Add Cost Ops team (T14) with 5 agents: model-economist, token-efficiency-engineer, vendor-arbitrage-analyst, grant-hunter, cost-ops-monitor - Add ai-cost-ops rules domain with 6 conventions (model routing, token budgets, caching, batch APIs, vendor abstraction, credit tracking) - Add team-cost-ops command with --task, --period, --provider flags - Update notification chains: data→cost-ops-monitor, infra→model-economist, retrospective-analyst→spec-compliance-auditor - Add intake routes: cost-ops, agent-performance Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(teams): add implement to cost-ops team accepts list Resolves agent/team accepts mismatch — token-efficiency-engineer accepts implement but the team definition only had investigate/review/plan/document. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(cost-ops): add multi-provider infra cost ticket to backlog Add detailed planning ticket for multi-provider infrastructure cost normalisation, routing, and cost-agent integration. Covers 9 providers (Anthropic, OpenAI, Google, Mistral, Cohere, self-hosted, Azure, AWS, GCP) with 3-phase delivery plan and cross-team dependency tracking. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(templates): resolve PR review comments from CodeRabbit - Fix protect-templates.sh: package name check uses correct "agentkit-forge-runtime" instead of "agentkit-forge" - Fix protect-templates.ps1: malformed path (missing separator before .agentkit) and same package name correction - Fix update-changelog.ps1: change .mjs to .cjs to match CommonJS require() syntax used in the inline Node script - Fix resolve-merge.sh: add fallback for {{defaultBranch}} placeholder - Fix AGENT_TEAMS.md: resolve three-way merge conflict markers left by sync engine, keeping user formatting + implement in cost-ops Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(cost-ops): add WebSearch/WebFetch tools to cost-ops agents (#365) Enable web research capabilities for cost-ops team: - Add WebSearch and WebFetch to /team-cost-ops allowed-tools - Add WebSearch and WebFetch to model-economist, vendor-arbitrage-analyst, and grant-hunter agent preferred-tools - Add web intake expansion ticket (P2) for MCP crawler, Puppeteer integration, automated pricing refresh, and cross-session persistence - Regenerate sync outputs Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> * fix(teams): address CodeRabbit review findings on strategic-ops PR - Lazy-load js-yaml in cli.mjs after ensureDependencies() to prevent crash when node_modules is missing - Convert YAML frontmatter to PowerShell comment blocks in all 6 PS1 templates to fix invalid PowerShell syntax - Fix protect-templates hook path: use 3 parent traversals to reach .agentkit/package.json from hooks directory - Remove schema-invalid 'phase' field from ai-cost-ops rule domain - Narrow strategic-ops scope: replace **/* catch-all with specific files - Add strategic-ops to cost-ops handoff-chain for consistency - Add Write tool to spec-compliance-auditor, vendor-arbitrage-analyst, and grant-hunter agents - Fix glob matching in resolve-merge.sh (use regex instead of broken sed strip) - Add merge failure vs conflict detection in resolve-merge.ps1 - Add branch existence check in setup-agentkit-branch-governance scripts - Add gh CLI preflight check in sync-split-pr.ps1 - Deduplicate branch protection loop when defaultBranch is 'main' - Fix applies-to glob: docs/planning/cost/** → docs/planning/cost-governance/** - Fix non-canonical doc paths in intake-agent-proposal.md - Add changelog entries for new teams, agents, and analysis engine - Resolve AGENT_TEAMS.md merge conflict (accept narrowed scope) - Run prettier on all modified files Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(templates): add gh auth preflight and changelog divider handling - sync-split-pr.ps1: add gh auth status check before side effects - update-changelog.ps1: stop before --- divider when appending entries Addresses CodeRabbit review comments #7 and #13 on PR #356. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(sync): set executable permission on analyze-agents.sh Linux CI sync produces +x permissions; align local to match. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(templates): address CodeRabbit review round 3-4 findings - Fix YAML frontmatter in copilot agent template: use double quotes for description field to handle apostrophes (CRITICAL) - Fix protect-templates.sh/ps1 path traversal: correct parent directory count for .agentkit/package.json source repo detection - Add $PSNativeCommandUseErrorActionPreference to sync-split-pr.ps1 so native command failures (git, pnpm, gh) are treated as fatal - Replace try/catch with $LASTEXITCODE check for gh auth status - Deduplicate branch loop in setup-agentkit-branch-governance.sh when defaultBranch equals 'main' - Fix duplicate verification echo lines in governance scripts Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * style(docs): fix prettier formatting on planning documents Run prettier --write on web-intake-expansion.md and intake-agent-proposal.md to fix CI formatting check. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(tests): isolate render target gating tests with fresh temp dirs Tests in the "render target gating" describe block shared a single temp directory via beforeAll/afterAll. The first test ran --only claude (generating .claude/ files), and the second ran --only warp expecting no Claude files — but leftovers from test 1 caused the assertion to fail. Changing to beforeEach/afterEach gives each test a clean directory. Closes #377 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(commands): add /start command as new user entry point Adds a context-aware triage command that detects repository state (fresh clone, post-discovery, mid-session, uncommitted work) and guides users to the right command or team for their goal. Includes team routing table, 4 contextual flows, and decision guidance for when users don't know which team to use. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * refactor(commands): add Arguments and State Management sections to /start Addresses TEAMFORGE validation findings: - Add dedicated Arguments section documenting $ARGUMENTS handling - Add State Management section (reads/writes inventory) - Fix frontmatter: remove misleading generated_by field - Add explicit "manually authored" comment header https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): add /start to spec and template for cross-repo generation Moves /start from a hand-authored command to a proper spec-driven, sync-generated command available to any repo that adopts AgentKit Forge. - Add start command definition to commands.yaml (no feature gate — always on) - Create start.md template in .agentkit/templates/claude/commands/ - Add /start to CLAUDE.md Quick Reference table template https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after adding /start command Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): make /start team routing dynamic instead of hardcoded Replace the static team routing table with dynamic discovery: 1. Read AGENT_TEAMS.md (from /discover) at runtime 2. Fall back to .agentkit/spec/teams.yaml 3. Fall back to /team-* command frontmatter This ensures /start always reflects the actual teams configured in any repo, rather than a hardcoded list that could go stale. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after dynamic routing change Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add interactive TUI entry point with hybrid UI Replace static markdown output with an ink-based terminal UI that combines two modes: a guided conversation flow for first-run users and a fuzzy-searchable command palette for returning users. A persistent status bar shows repo state at a glance (branch, phase, backlog count, working tree status). - Context detection module mirrors /start Phase 1 signals - ConversationFlow: branching dialogue tree (choose-your-own-adventure) - CommandPalette: fuzzy search with context-ranked star recommendations - StatusBar: tmux-style persistent strip with color-coded segments - Supports --json flag for scripting/piping https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add test suite, error handling, and refactor for production readiness - Add vitest test infrastructure with 102 tests across 7 files - Coverage: 95.58% statements, 90.81% branches, 96.72% functions - Extract conversation tree to separate config module for testability - Add error boundary to App component for graceful error display - Add --help flag with usage documentation - Add TTY detection with JSON fallback for non-interactive environments - Add SIGINT/SIGTERM signal handling for clean exit https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore: add coverage to gitignore, include plan and workspace config https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — unused code, git cwd, magic numbers - Call exit() after command selection so Ink process terminates - Remove unused ctx prop from Header component - Fix git commands to use -C flag with root path parameter - Extract dumpContextJson() helper to deduplicate JSON output logic - Add comment explaining hardcoded team filter exclusion - Replace magic numbers with named constants (FUSE_THRESHOLD, RECOMMENDED_SCORE, MAX_BRANCH_LENGTH) - Remove unused ink-spinner dependency - Add test verifying git -C flag passes root correctly https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — security, correctness, test quality - CRITICAL: Replace execSync shell interpolation with execFileSync to prevent command injection via root parameter in detect.js - CRITICAL: Remove phantom --external:ink-spinner from build script and switch npx to direct esbuild invocation - HIGH: Fix exit race condition — use useEffect instead of setTimeout - HIGH: Wire up onSelect callback in ConversationFlow so Guide mode triggers the result screen in App - HIGH: Destructure and accept ctx prop in ConversationFlow - HIGH: Add back-navigation (Escape) in ConversationFlow - HIGH: Guard against undefined team.focus in commands.js tags - MEDIUM: Use functional setCursor form to avoid stale closures - MEDIUM: Key commandIndices Map by string id instead of object identity - MEDIUM: Improve parseTeams header detection (drop first row approach) - MEDIUM: Filter completed/done/closed items from backlogCount - MEDIUM: Extract shared makeCtx test utility across all test files - MEDIUM: Add null guard to StatusBar truncate helper - LOW: Validate orchestratorPhase is a number in range 1-5 - LOW: Fix pnpm-workspace.yaml list syntax - Replace all setTimeout in tests with vi.waitFor deterministic waits https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(engine): add pre-sync commit guard and interactive apply mode Adds two safety features to the sync pipeline: 1. Pre-sync commit guard: Detects uncommitted changes in protected directories (.agentkit/engines, spec, overlays) before sync runs. In TTY mode, prompts to abort, stash, or continue. In non-TTY mode (CI), prints a warning and proceeds. 2. Interactive apply mode: After rendering, shows a change summary and prompts: apply all / skip all / prompt each file. Per-file prompt supports show-diff and apply-all-remaining. Default in TTY; bypassed with --yes, --no-prompt, or --force. New module: sync-guard.mjs with 4 exported functions and 7 tests. New CLI flags: --yes, --no-prompt for non-interactive sync. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore(sync): regenerate outputs after branch merges Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore(sync): regenerate outputs after merge of new-user-entry-point Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(engine): add configurable package manager and fix review findings - Add `stack.packageManager` field to project.yaml (pnpm | npm | yarn) - Derive helper template vars (pmInstall, pmRun, pmExec, pmLockfile, etc.) - Update CLAUDE.md template and hook/workflow templates to use {{packageManager}} - Fix sync-guard to exclude .agentkit/spec from protected dirs and add try/catch - Remove duplicate cost-ops team definition from teams.yaml - Pin all dependency versions in package.json (remove ^ prefixes) - Add vitest coverage thresholds (80% statements/branches/functions/lines) - Fix src/start/ code quality: null guards, exit delay, error boundaries - Harden consolidate-branches.sh: self-resolution guard, stash restore - Regenerate all 533 output files via agentkit sync Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore(engine): add brand color palette variables to sync vars Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(ci): fix test race condition, workspace config, and lockfile - Fix ConversationFlow test: wait for 'Got it' before asserting hint text - Add packages field to pnpm-workspace.yaml for proper workspace resolution - Regenerate lockfile after version pinning (removed ^ prefixes) - Remove accidental .agentkit/templates/src/ artifacts Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(start): add event loop yields to ConversationFlow tests ink-select-input needs setImmediate yields after a new menu renders before it can process ENTER keypresses. Without this, the second ENTER in leaf-selection tests was swallowed, causing intermittent failures. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat(commands): add /start command as new user entry point Adds a context-aware triage command that detects repository state (fresh clone, post-discovery, mid-session, uncommitted work) and guides users to the right command or team for their goal. Includes team routing table, 4 contextual flows, and decision guidance for when users don't know which team to use. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * refactor(commands): add Arguments and State Management sections to /start Addresses TEAMFORGE validation findings: - Add dedicated Arguments section documenting $ARGUMENTS handling - Add State Management section (reads/writes inventory) - Fix frontmatter: remove misleading generated_by field - Add explicit "manually authored" comment header https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): add /start to spec and template for cross-repo generation Moves /start from a hand-authored command to a proper spec-driven, sync-generated command available to any repo that adopts AgentKit Forge. - Add start command definition to commands.yaml (no feature gate — always on) - Create start.md template in .agentkit/templates/claude/commands/ - Add /start to CLAUDE.md Quick Reference table template https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after adding /start command Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): make /start team routing dynamic instead of hardcoded Replace the static team routing table with dynamic discovery: 1. Read AGENT_TEAMS.md (from /discover) at runtime 2. Fall back to .agentkit/spec/teams.yaml 3. Fall back to /team-* command frontmatter This ensures /start always reflects the actual teams configured in any repo, rather than a hardcoded list that could go stale. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after dynamic routing change Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add interactive TUI entry point with hybrid UI Replace static markdown output with an ink-based terminal UI that combines two modes: a guided conversation flow for first-run users and a fuzzy-searchable command palette for returning users. A persistent status bar shows repo state at a glance (branch, phase, backlog count, working tree status). - Context detection module mirrors /start Phase 1 signals - ConversationFlow: branching dialogue tree (choose-your-own-adventure) - CommandPalette: fuzzy search with context-ranked star recommendations - StatusBar: tmux-style persistent strip with color-coded segments - Supports --json flag for scripting/piping https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add test suite, error handling, and refactor for production readiness - Add vitest test infrastructure with 102 tests across 7 files - Coverage: 95.58% statements, 90.81% branches, 96.72% functions - Extract conversation tree to separate config module for testability - Add error boundary to App component for graceful error display - Add --help flag with usage documentation - Add TTY detection with JSON fallback for non-interactive environments - Add SIGINT/SIGTERM signal handling for clean exit https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore: add coverage to gitignore, include plan and workspace config https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — unused code, git cwd, magic numbers - Call exit() after command selection so Ink process terminates - Remove unused ctx prop from Header component - Fix git commands to use -C flag with root path parameter - Extract dumpContextJson() helper to deduplicate JSON output logic - Add comment explaining hardcoded team filter exclusion - Replace magic numbers with named constants (FUSE_THRESHOLD, RECOMMENDED_SCORE, MAX_BRANCH_LENGTH) - Remove unused ink-spinner dependency - Add test verifying git -C flag passes root correctly https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — security, correctness, test quality - CRITICAL: Replace execSync shell interpolation with execFileSync to prevent command injection via root parameter in detect.js - CRITICAL: Remove phantom --external:ink-spinner from build script and switch npx to direct esbuild invocation - HIGH: Fix exit race condition — use useEffect instead of setTimeout - HIGH: Wire up onSelect callback in ConversationFlow so Guide mode triggers the result screen in App - HIGH: Destructure and accept ctx prop in ConversationFlow - HIGH: Add back-navigation (Escape) in ConversationFlow - HIGH: Guard against undefined team.focus in commands.js tags - MEDIUM: Use functional setCursor form to avoid stale closures - MEDIUM: Key commandIndices Map by string id instead of object identity - MEDIUM: Improve parseTeams header detection (drop first row approach) - MEDIUM: Filter completed/done/closed items from backlogCount - MEDIUM: Extract shared makeCtx test utility across all test files - MEDIUM: Add null guard to StatusBar truncate helper - LOW: Validate orchestratorPhase is a number in range 1-5 - LOW: Fix pnpm-workspace.yaml list syntax - Replace all setTimeout in tests with vi.waitFor deterministic waits https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * test(start): add coverage for result screen exit path Add App-level test that navigates through ConversationFlow to a leaf node and verifies the result screen text is rendered before exit(). Confirms the synchronous useEffect exit is safe — React commits the render (Ink captures the frame) before useEffect fires. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore: update generated sync output timestamps Generated files updated with current sync date from dev merge. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW --------- Co-authored-by: Claude <noreply@anthropic.com>
* Add start command: new user entry point with state detection (#387) * fix(commands): add AskUserQuestion to VALID_TOOLS and /start command The /start command session got stuck because AskUserQuestion was not included in the allowed-tools whitelist. This fix addresses three issues: 1. VALID_TOOLS in spec-validator was missing AskUserQuestion, TodoWrite, Agent, and NotebookEdit — preventing commands from declaring these Claude Code built-in tools in their allowed-tools. 2. The /start command template now explicitly includes AskUserQuestion in its allowed-tools frontmatter and instructs the agent to use it for interactive guided choices (Phase 3). 3. Added /start command spec to commands.yaml with AskUserQuestion as a declared tool dependency. Also adds a test case validating all four newly-added tools are accepted by the spec validator. https://claude.ai/code/session_01Qh3Xk3jFkVdeRAXTqLvq3M * fix(commands): remove unrendered Handlebars comment from start.md output The generated .claude/commands/start.md contained a raw {{! ... }} Handlebars comment that was not processed by the sync engine. Remove it so the generated output is clean Markdown. https://claude.ai/code/session_01Qh3Xk3jFkVdeRAXTqLvq3M --------- * Add configurable prefix to kits commands (#388) * feat(sync): add configurable command prefix for generated slash commands Add `commandPrefix` setting to overlay settings that namespaces all generated slash commands across platforms: - Claude Code: subdirectory strategy (kits/check.md → /project:kits:check) - Cursor/Windsurf/Copilot/Codex: filename prefix (kits-check.md → /kits-check) - Team commands excluded from prefixing (already namespaced) Changes: - Add resolveCommandPath() helper with subdirectory/filename strategies - Update syncClaudeCommands, syncClaudeSkills, syncCursorCommands, syncWindsurfCommands, syncCopilotPrompts, syncCodexSkills - Add commandPrefix to vars from overlay settings - Add commandPrefixedName to buildCommandVars - Add 16 unit + integration tests (all pass, 93 existing tests unaffected) Default is null (no prefix) for full backwards compatibility. https://claude.ai/code/session_01EBjmVEhi7fP2huAL3SBR6p * fix(sync): address review findings for command prefix - Remove unused afterAll import from test file - Add clarifying comment that non-spec command files are also prefixed - Add 2 integration tests verifying commandPrefixedName template variable renders correctly with and without prefix https://claude.ai/code/session_01EBjmVEhi7fP2huAL3SBR6p --------- * fix(ci): CI remediation — package manager, review findings, test stability (#390) * fix(ci): resolve 7 bugs from project review - BUG-001: Replace flaky discover test with controlled temp fixture - BUG-002: Run prettier --write to fix formatting drift - BUG-003: Add form-template detection skip in issue label validation - BUG-005: Change claude.yml to self-hosted runner - BUG-006: Align branch protection required status checks with project.yaml - BUG-007: Fix command injection in resolve-merge.sh (use grep -F) * docs: update changelog, add planning registry review findings - Add changelog entries for Wave 1-3 fixes (Added/Changed/Fixed/Removed) - Add Project Review Findings section to planning registry (PR-001 to PR-014) - Update planning docs after sync merge * feat(review): add --generate-plans flag to project-review command Add Phase 2.5 plan generation after project review findings. When --generate-plans is passed (default: true), scaffold plan files from critical/high findings into docs/planning/review-findings/. Also includes sync cleanup of stale cursor/windsurf settings. * chore(sync): regenerate all outputs after project review fixes * feat(cli): dynamic flag loading from commands.yaml + context-aware template hook - Replace ~200 lines of hardcoded VALID_FLAGS/FLAG_TYPES with loadCommandFlags() that reads flag definitions from commands.yaml at startup - CLI_INTERNAL_FLAGS/CLI_INTERNAL_FLAG_TYPES cover commands not in commands.yaml - Self-validation warns at startup if any flag is missing a type definition - Update cli.test.mjs to validate CLI_INTERNAL_FLAGS consistency - Fix scaffold-once orphan bug: carry forward manifest entries for files skipped by scaffold-once so orphan cleanup does not delete them - Make protect-templates hook context-aware: skip protection in the agentkit-forge source repo (detected via package.json name) so maintainer agents can edit templates; block only in downstream repos * feat(sync): add managed-mode script templates for downstream repos Add 14 script templates (.agentkit/templates/scripts/) with `managed` scaffold mode so downstream repos receive script updates via three-way merge while preserving local customizations. Templates include: create-doc, update-changelog, validate-documentation, validate-numbering, check-documentation-requirement, sync-issues, sync-split-pr, setup-agentkit-branch-governance, and resolve-merge (both .sh and .ps1 variants where applicable). Parameterized templates use {{defaultBranch}} and branch protection variables from project.yaml. Engine wired via syncScripts() under doc-scaffolding feature gate. * feat(teams): add TeamForge meta-team for agent team creation (cogmesh #130) Add the TEAMFORGE meta-team (T11) — a structured pipeline for creating, validating, and deploying new agent team specifications. Adapted from cogmesh #130 with a simplified 6-agent pipeline: - input-clarifier: assess requests, extract constraints - mission-definer: lock team definition (ID, scope, accepts) - role-architect: design agent roles and dependencies - prompt-engineer: write agent descriptions and rules - flow-designer: design team command and integration points - team-validator: quality gate for spec consistency Includes /team-forge command with --task flag (create-team, validate-team, audit-teams, update-team) and planning doc. * feat(teams): add Strategic Ops team for cross-project coordination Add the STRATEGIC OPS team (T12) — handles framework governance, portfolio analysis, adoption strategy, impact assessment, and release coordination across all repos using AgentKit Forge. 5-agent pipeline: - portfolio-analyst: inventory repos, detect drift, adoption metrics - governance-advisor: versioning strategy, breaking change protocols - adoption-strategist: onboarding, migration paths, rollout plans - impact-assessor: blast radius analysis for template/spec changes - release-coordinator: version bumps, sync waves, release comms Includes /team-strategic-ops command with --task and --scope flags. * feat(agents): add agent/team relationship matrix analysis engine + scripts Add comprehensive agent/team relationship analysis with 8 cross-reference matrices and 10 supplementary analyses (orphans, cycles, bottlenecks, reachability, critical path, notification amplifiers, etc.). - Fix YAML structure: strategic-ops agents now under own top-level key - Add explicit agents: lists to forge + strategic-ops teams in teams.yaml - Add consolidation detection responsibilities to portfolio-analyst - Create agent-analysis.mjs engine module (loadFullAgentGraph + renderers) - Wire analyze-agents CLI command with --output/--matrix/--format flags - Add managed-scaffold script templates (bash + PowerShell) - Integrate into sync pipeline (auto-regenerates matrix on spec changes) - Add 33 tests covering all matrices, analyses, and edge cases * chore: update documentation files and add plan template - Add trailing newlines to Cursor command documentation files for consistency - Add new plan template files for project planning - Improve markdown table formatting in Claude skills documentation - Remove obsolete .clinerules/testing.md file - Update various rule files with better formatting and advisory rule alignment * feat(agents): add spec-compliance-auditor feedback loop + Cost Ops team (T14) - Add spec-compliance-auditor to operations category (quality team) — closes the feedback loop between agent specs and actual behavior - Add Cost Ops team (T14) with 5 agents: model-economist, token-efficiency-engineer, vendor-arbitrage-analyst, grant-hunter, cost-ops-monitor - Add ai-cost-ops rules domain with 6 conventions (model routing, token budgets, caching, batch APIs, vendor abstraction, credit tracking) - Add team-cost-ops command with --task, --period, --provider flags - Update notification chains: data→cost-ops-monitor, infra→model-economist, retrospective-analyst→spec-compliance-auditor - Add intake routes: cost-ops, agent-performance * fix(teams): add implement to cost-ops team accepts list Resolves agent/team accepts mismatch — token-efficiency-engineer accepts implement but the team definition only had investigate/review/plan/document. * feat(cost-ops): add multi-provider infra cost ticket to backlog Add detailed planning ticket for multi-provider infrastructure cost normalisation, routing, and cost-agent integration. Covers 9 providers (Anthropic, OpenAI, Google, Mistral, Cohere, self-hosted, Azure, AWS, GCP) with 3-phase delivery plan and cross-team dependency tracking. * fix(templates): resolve PR review comments from CodeRabbit - Fix protect-templates.sh: package name check uses correct "agentkit-forge-runtime" instead of "agentkit-forge" - Fix protect-templates.ps1: malformed path (missing separator before .agentkit) and same package name correction - Fix update-changelog.ps1: change .mjs to .cjs to match CommonJS require() syntax used in the inline Node script - Fix resolve-merge.sh: add fallback for {{defaultBranch}} placeholder - Fix AGENT_TEAMS.md: resolve three-way merge conflict markers left by sync engine, keeping user formatting + implement in cost-ops * feat(cost-ops): add WebSearch/WebFetch tools to cost-ops agents Enable web research capabilities for cost-ops team: - Add WebSearch and WebFetch to /team-cost-ops allowed-tools - Add WebSearch and WebFetch to model-economist, vendor-arbitrage-analyst, and grant-hunter agent preferred-tools - Add web intake expansion ticket (P2) for MCP crawler, Puppeteer integration, automated pricing refresh, and cross-session persistence - Regenerate sync outputs * feat(cost-ops): add Cost Ops team, agents, and multi-provider cost ticket (#364) * feat(agents): add spec-compliance-auditor feedback loop + Cost Ops team (T14) - Add spec-compliance-auditor to operations category (quality team) — closes the feedback loop between agent specs and actual behavior - Add Cost Ops team (T14) with 5 agents: model-economist, token-efficiency-engineer, vendor-arbitrage-analyst, grant-hunter, cost-ops-monitor - Add ai-cost-ops rules domain with 6 conventions (model routing, token budgets, caching, batch APIs, vendor abstraction, credit tracking) - Add team-cost-ops command with --task, --period, --provider flags - Update notification chains: data→cost-ops-monitor, infra→model-economist, retrospective-analyst→spec-compliance-auditor - Add intake routes: cost-ops, agent-performance * fix(teams): add implement to cost-ops team accepts list Resolves agent/team accepts mismatch — token-efficiency-engineer accepts implement but the team definition only had investigate/review/plan/document. * feat(cost-ops): add multi-provider infra cost ticket to backlog Add detailed planning ticket for multi-provider infrastructure cost normalisation, routing, and cost-agent integration. Covers 9 providers (Anthropic, OpenAI, Google, Mistral, Cohere, self-hosted, Azure, AWS, GCP) with 3-phase delivery plan and cross-team dependency tracking. * fix(templates): resolve PR review comments from CodeRabbit - Fix protect-templates.sh: package name check uses correct "agentkit-forge-runtime" instead of "agentkit-forge" - Fix protect-templates.ps1: malformed path (missing separator before .agentkit) and same package name correction - Fix update-changelog.ps1: change .mjs to .cjs to match CommonJS require() syntax used in the inline Node script - Fix resolve-merge.sh: add fallback for {{defaultBranch}} placeholder - Fix AGENT_TEAMS.md: resolve three-way merge conflict markers left by sync engine, keeping user formatting + implement in cost-ops * feat(cost-ops): add WebSearch/WebFetch tools to cost-ops agents (#365) Enable web research capabilities for cost-ops team: - Add WebSearch and WebFetch to /team-cost-ops allowed-tools - Add WebSearch and WebFetch to model-economist, vendor-arbitrage-analyst, and grant-hunter agent preferred-tools - Add web intake expansion ticket (P2) for MCP crawler, Puppeteer integration, automated pricing refresh, and cross-session persistence - Regenerate sync outputs --------- * fix(teams): address CodeRabbit review findings on strategic-ops PR - Lazy-load js-yaml in cli.mjs after ensureDependencies() to prevent crash when node_modules is missing - Convert YAML frontmatter to PowerShell comment blocks in all 6 PS1 templates to fix invalid PowerShell syntax - Fix protect-templates hook path: use 3 parent traversals to reach .agentkit/package.json from hooks directory - Remove schema-invalid 'phase' field from ai-cost-ops rule domain - Narrow strategic-ops scope: replace **/* catch-all with specific files - Add strategic-ops to cost-ops handoff-chain for consistency - Add Write tool to spec-compliance-auditor, vendor-arbitrage-analyst, and grant-hunter agents - Fix glob matching in resolve-merge.sh (use regex instead of broken sed strip) - Add merge failure vs conflict detection in resolve-merge.ps1 - Add branch existence check in setup-agentkit-branch-governance scripts - Add gh CLI preflight check in sync-split-pr.ps1 - Deduplicate branch protection loop when defaultBranch is 'main' - Fix applies-to glob: docs/planning/cost/** → docs/planning/cost-governance/** - Fix non-canonical doc paths in intake-agent-proposal.md - Add changelog entries for new teams, agents, and analysis engine - Resolve AGENT_TEAMS.md merge conflict (accept narrowed scope) - Run prettier on all modified files * fix(templates): add gh auth preflight and changelog divider handling - sync-split-pr.ps1: add gh auth status check before side effects - update-changelog.ps1: stop before --- divider when appending entries Addresses CodeRabbit review comments #7 and #13 on PR #356. * fix(sync): set executable permission on analyze-agents.sh Linux CI sync produces +x permissions; align local to match. * fix(templates): address CodeRabbit review round 3-4 findings - Fix YAML frontmatter in copilot agent template: use double quotes for description field to handle apostrophes (CRITICAL) - Fix protect-templates.sh/ps1 path traversal: correct parent directory count for .agentkit/package.json source repo detection - Add $PSNativeCommandUseErrorActionPreference to sync-split-pr.ps1 so native command failures (git, pnpm, gh) are treated as fatal - Replace try/catch with $LASTEXITCODE check for gh auth status - Deduplicate branch loop in setup-agentkit-branch-governance.sh when defaultBranch equals 'main' - Fix duplicate verification echo lines in governance scripts * style(docs): fix prettier formatting on planning documents Run prettier --write on web-intake-expansion.md and intake-agent-proposal.md to fix CI formatting check. * fix(tests): isolate render target gating tests with fresh temp dirs Tests in the "render target gating" describe block shared a single temp directory via beforeAll/afterAll. The first test ran --only claude (generating .claude/ files), and the second ran --only warp expecting no Claude files — but leftovers from test 1 caused the assertion to fail. Changing to beforeEach/afterEach gives each test a clean directory. Closes #377 * feat(commands): add /start command as new user entry point Adds a context-aware triage command that detects repository state (fresh clone, post-discovery, mid-session, uncommitted work) and guides users to the right command or team for their goal. Includes team routing table, 4 contextual flows, and decision guidance for when users don't know which team to use. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * refactor(commands): add Arguments and State Management sections to /start Addresses TEAMFORGE validation findings: - Add dedicated Arguments section documenting $ARGUMENTS handling - Add State Management section (reads/writes inventory) - Fix frontmatter: remove misleading generated_by field - Add explicit "manually authored" comment header https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): add /start to spec and template for cross-repo generation Moves /start from a hand-authored command to a proper spec-driven, sync-generated command available to any repo that adopts AgentKit Forge. - Add start command definition to commands.yaml (no feature gate — always on) - Create start.md template in .agentkit/templates/claude/commands/ - Add /start to CLAUDE.md Quick Reference table template https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after adding /start command Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): make /start team routing dynamic instead of hardcoded Replace the static team routing table with dynamic discovery: 1. Read AGENT_TEAMS.md (from /discover) at runtime 2. Fall back to .agentkit/spec/teams.yaml 3. Fall back to /team-* command frontmatter This ensures /start always reflects the actual teams configured in any repo, rather than a hardcoded list that could go stale. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after dynamic routing change Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add interactive TUI entry point with hybrid UI Replace static markdown output with an ink-based terminal UI that combines two modes: a guided conversation flow for first-run users and a fuzzy-searchable command palette for returning users. A persistent status bar shows repo state at a glance (branch, phase, backlog count, working tree status). - Context detection module mirrors /start Phase 1 signals - ConversationFlow: branching dialogue tree (choose-your-own-adventure) - CommandPalette: fuzzy search with context-ranked star recommendations - StatusBar: tmux-style persistent strip with color-coded segments - Supports --json flag for scripting/piping https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add test suite, error handling, and refactor for production readiness - Add vitest test infrastructure with 102 tests across 7 files - Coverage: 95.58% statements, 90.81% branches, 96.72% functions - Extract conversation tree to separate config module for testability - Add error boundary to App component for graceful error display - Add --help flag with usage documentation - Add TTY detection with JSON fallback for non-interactive environments - Add SIGINT/SIGTERM signal handling for clean exit https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore: add coverage to gitignore, include plan and workspace config https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — unused code, git cwd, magic numbers - Call exit() after command selection so Ink process terminates - Remove unused ctx prop from Header component - Fix git commands to use -C flag with root path parameter - Extract dumpContextJson() helper to deduplicate JSON output logic - Add comment explaining hardcoded team filter exclusion - Replace magic numbers with named constants (FUSE_THRESHOLD, RECOMMENDED_SCORE, MAX_BRANCH_LENGTH) - Remove unused ink-spinner dependency - Add test verifying git -C flag passes root correctly https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — security, correctness, test quality - CRITICAL: Replace execSync shell interpolation with execFileSync to prevent command injection via root parameter in detect.js - CRITICAL: Remove phantom --external:ink-spinner from build script and switch npx to direct esbuild invocation - HIGH: Fix exit race condition — use useEffect instead of setTimeout - HIGH: Wire up onSelect callback in ConversationFlow so Guide mode triggers the result screen in App - HIGH: Destructure and accept ctx prop in ConversationFlow - HIGH: Add back-navigation (Escape) in ConversationFlow - HIGH: Guard against undefined team.focus in commands.js tags - MEDIUM: Use functional setCursor form to avoid stale closures - MEDIUM: Key commandIndices Map by string id instead of object identity - MEDIUM: Improve parseTeams header detection (drop first row approach) - MEDIUM: Filter completed/done/closed items from backlogCount - MEDIUM: Extract shared makeCtx test utility across all test files - MEDIUM: Add null guard to StatusBar truncate helper - LOW: Validate orchestratorPhase is a number in range 1-5 - LOW: Fix pnpm-workspace.yaml list syntax - Replace all setTimeout in tests with vi.waitFor deterministic waits https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(engine): add pre-sync commit guard and interactive apply mode Adds two safety features to the sync pipeline: 1. Pre-sync commit guard: Detects uncommitted changes in protected directories (.agentkit/engines, spec, overlays) before sync runs. In TTY mode, prompts to abort, stash, or continue. In non-TTY mode (CI), prints a warning and proceeds. 2. Interactive apply mode: After rendering, shows a change summary and prompts: apply all / skip all / prompt each file. Per-file prompt supports show-diff and apply-all-remaining. Default in TTY; bypassed with --yes, --no-prompt, or --force. New module: sync-guard.mjs with 4 exported functions and 7 tests. New CLI flags: --yes, --no-prompt for non-interactive sync. * chore(sync): regenerate outputs after branch merges * chore(sync): regenerate outputs after merge of new-user-entry-point * feat(engine): add configurable package manager and fix review findings - Add `stack.packageManager` field to project.yaml (pnpm | npm | yarn) - Derive helper template vars (pmInstall, pmRun, pmExec, pmLockfile, etc.) - Update CLAUDE.md template and hook/workflow templates to use {{packageManager}} - Fix sync-guard to exclude .agentkit/spec from protected dirs and add try/catch - Remove duplicate cost-ops team definition from teams.yaml - Pin all dependency versions in package.json (remove ^ prefixes) - Add vitest coverage thresholds (80% statements/branches/functions/lines) - Fix src/start/ code quality: null guards, exit delay, error boundaries - Harden consolidate-branches.sh: self-resolution guard, stash restore - Regenerate all 533 output files via agentkit sync * chore(engine): add brand color palette variables to sync vars * fix(ci): fix test race condition, workspace config, and lockfile - Fix ConversationFlow test: wait for 'Got it' before asserting hint text - Add packages field to pnpm-workspace.yaml for proper workspace resolution - Regenerate lockfile after version pinning (removed ^ prefixes) - Remove accidental .agentkit/templates/src/ artifacts * fix(start): add event loop yields to ConversationFlow tests ink-select-input needs setImmediate yields after a new menu renders before it can process ENTER keypresses. Without this, the second ENTER in leaf-selection tests was swallowed, causing intermittent failures. --------- * fix(spec): correct githubSlug to phoenixvc/agentkit-forge (#391) * Add entry point for new framework users (#389) * feat(commands): add /start command as new user entry point Adds a context-aware triage command that detects repository state (fresh clone, post-discovery, mid-session, uncommitted work) and guides users to the right command or team for their goal. Includes team routing table, 4 contextual flows, and decision guidance for when users don't know which team to use. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * refactor(commands): add Arguments and State Management sections to /start Addresses TEAMFORGE validation findings: - Add dedicated Arguments section documenting $ARGUMENTS handling - Add State Management section (reads/writes inventory) - Fix frontmatter: remove misleading generated_by field - Add explicit "manually authored" comment header https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): add /start to spec and template for cross-repo generation Moves /start from a hand-authored command to a proper spec-driven, sync-generated command available to any repo that adopts AgentKit Forge. - Add start command definition to commands.yaml (no feature gate — always on) - Create start.md template in .agentkit/templates/claude/commands/ - Add /start to CLAUDE.md Quick Reference table template https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after adding /start command Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): make /start team routing dynamic instead of hardcoded Replace the static team routing table with dynamic discovery: 1. Read AGENT_TEAMS.md (from /discover) at runtime 2. Fall back to .agentkit/spec/teams.yaml 3. Fall back to /team-* command frontmatter This ensures /start always reflects the actual teams configured in any repo, rather than a hardcoded list that could go stale. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after dynamic routing change Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add interactive TUI entry point with hybrid UI Replace static markdown output with an ink-based terminal UI that combines two modes: a guided conversation flow for first-run users and a fuzzy-searchable command palette for returning users. A persistent status bar shows repo state at a glance (branch, phase, backlog count, working tree status). - Context detection module mirrors /start Phase 1 signals - ConversationFlow: branching dialogue tree (choose-your-own-adventure) - CommandPalette: fuzzy search with context-ranked star recommendations - StatusBar: tmux-style persistent strip with color-coded segments - Supports --json flag for scripting/piping https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add test suite, error handling, and refactor for production readiness - Add vitest test infrastructure with 102 tests across 7 files - Coverage: 95.58% statements, 90.81% branches, 96.72% functions - Extract conversation tree to separate config module for testability - Add error boundary to App component for graceful error display - Add --help flag with usage documentation - Add TTY detection with JSON fallback for non-interactive environments - Add SIGINT/SIGTERM signal handling for clean exit https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore: add coverage to gitignore, include plan and workspace config https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — unused code, git cwd, magic numbers - Call exit() after command selection so Ink process terminates - Remove unused ctx prop from Header component - Fix git commands to use -C flag with root path parameter - Extract dumpContextJson() helper to deduplicate JSON output logic - Add comment explaining hardcoded team filter exclusion - Replace magic numbers with named constants (FUSE_THRESHOLD, RECOMMENDED_SCORE, MAX_BRANCH_LENGTH) - Remove unused ink-spinner dependency - Add test verifying git -C flag passes root correctly https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — security, correctness, test quality - CRITICAL: Replace execSync shell interpolation with execFileSync to prevent command injection via root parameter in detect.js - CRITICAL: Remove phantom --external:ink-spinner from build script and switch npx to direct esbuild invocation - HIGH: Fix exit race condition — use useEffect instead of setTimeout - HIGH: Wire up onSelect callback in ConversationFlow so Guide mode triggers the result screen in App - HIGH: Destructure and accept ctx prop in ConversationFlow - HIGH: Add back-navigation (Escape) in ConversationFlow - HIGH: Guard against undefined team.focus in commands.js tags - MEDIUM: Use functional setCursor form to avoid stale closures - MEDIUM: Key commandIndices Map by string id instead of object identity - MEDIUM: Improve parseTeams header detection (drop first row approach) - MEDIUM: Filter completed/done/closed items from backlogCount - MEDIUM: Extract shared makeCtx test utility across all test files - MEDIUM: Add null guard to StatusBar truncate helper - LOW: Validate orchestratorPhase is a number in range 1-5 - LOW: Fix pnpm-workspace.yaml list syntax - Replace all setTimeout in tests with vi.waitFor deterministic waits https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * test(start): add coverage for result screen exit path Add App-level test that navigates through ConversationFlow to a leaf node and verifies the result screen text is rendered before exit(). Confirms the synchronous useEffect exit is safe — React commits the render (Ink captures the frame) before useEffect fires. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore: update generated sync output timestamps Generated files updated with current sync date from dev merge. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW --------- * fix: caldues heuristics (#398) --------- Co-authored-by: Claude <noreply@anthropic.com>
- Fix Prettier formatting across engine src and start components - Resolve 381 markdown lint errors (MD040, MD024, MD036, MD029, MD022, MD001) - Add markdownlint config rules for intentional doc patterns - Add .claude/worktrees to prettierignore to exclude external branches - Enable markdownlint MD024/MD026 for duplicate headings and trailing colons All quality checks now pass: Prettier (0 errors), Markdown lint (0 errors), Tests (111/111), Build (28.9kb)
… to '2026-03-13'. This appears to be a routine timestamp update across all the AgentKit Forge generated files.
Add detailed feedback on AgentKit Forge v3.1.0 integration, focusing on: - Windows line-ending issues and multi-editor sync behavior - Documentation scaffold-once limitations and override challenges - Unresolved placeholder warnings lacking diagnostics - Windows-specific pnpm execution problems
Clarified that modifications to `.agentkit` files are permitted in the agentkit-forge repository, while upstream directories remain protected. This ensures users understand the editing boundaries for project configuration and template files.
Made-with: Cursor
Made-with: Cursor
* fix(infra): resolve container app fqdn attribute and format code * chore(sync): update AGENT_BACKLOG.md and other files for task management - Enhanced AGENT_BACKLOG.md with detailed task scopes for CI pipeline configuration and test framework setup. - Added new docker-compose.yml for local/staging validation of the framework. - Updated CONTRIBUTING.md to include documentation hub link in the Discovery phase. - Introduced README.md files in db, infra, and migrations directories to clarify their purpose for adopters. - Added API conventions documentation to guide adopters on structuring their APIs. - Created implementation plan for state management improvements and added relevant tests. - Regenerated outputs across various files to reflect recent changes and ensure consistency.
* chore(ci): reduce CodeQL to weekly schedule + manual trigger Removes push and pull_request triggers to reduce GitHub Actions costs. Scans were running on every PR including Renovate dependency updates. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
…adoption roadmap (#428) * docs(architecture): add tool-neutral agent hub findings, ADR-10, and adoption roadmap Comparative analysis of agentkit-forge sync engine vs Mystira.workspace hand-authored .agents/ pattern. Documents 5-phase adoption roadmap to converge both approaches: .agents/ as sync target, reflective guards, .readme.yaml generation, cross-session traces, and schema formalisation. Includes regenerated sync output (updated timestamps across all tools). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * docs(architecture): add competitive landscape and strategic research report Comprehensive analysis of the AI agent configuration & orchestration market: - 6 primary competitors profiled (Ruler, Agent OS, ai-rules-sync, agent-rules, Block ai-rules, AGENTS.md) - Evaluation matrix across 14 dimensions - SWOT analysis with evidence-based assessments - 12-KPI framework with baselines, targets, and scoring methodology - Tracking dashboard template and priority matrix - Market context: $8.5B market, 62% developer adoption, protocol convergence Key finding: Rules sync is commoditising; AgentKit Forge's moat is orchestration + governance + CI validation. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
…cord (#431) * feat: new entry points (#426) * Add start command: new user entry point with state detection (#387) * fix(commands): add AskUserQuestion to VALID_TOOLS and /start command The /start command session got stuck because AskUserQuestion was not included in the allowed-tools whitelist. This fix addresses three issues: 1. VALID_TOOLS in spec-validator was missing AskUserQuestion, TodoWrite, Agent, and NotebookEdit — preventing commands from declaring these Claude Code built-in tools in their allowed-tools. 2. The /start command template now explicitly includes AskUserQuestion in its allowed-tools frontmatter and instructs the agent to use it for interactive guided choices (Phase 3). 3. Added /start command spec to commands.yaml with AskUserQuestion as a declared tool dependency. Also adds a test case validating all four newly-added tools are accepted by the spec validator. https://claude.ai/code/session_01Qh3Xk3jFkVdeRAXTqLvq3M * fix(commands): remove unrendered Handlebars comment from start.md output The generated .claude/commands/start.md contained a raw {{! ... }} Handlebars comment that was not processed by the sync engine. Remove it so the generated output is clean Markdown. https://claude.ai/code/session_01Qh3Xk3jFkVdeRAXTqLvq3M --------- Co-authored-by: Claude <noreply@anthropic.com> * Add configurable prefix to kits commands (#388) * feat(sync): add configurable command prefix for generated slash commands Add `commandPrefix` setting to overlay settings that namespaces all generated slash commands across platforms: - Claude Code: subdirectory strategy (kits/check.md → /project:kits:check) - Cursor/Windsurf/Copilot/Codex: filename prefix (kits-check.md → /kits-check) - Team commands excluded from prefixing (already namespaced) Changes: - Add resolveCommandPath() helper with subdirectory/filename strategies - Update syncClaudeCommands, syncClaudeSkills, syncCursorCommands, syncWindsurfCommands, syncCopilotPrompts, syncCodexSkills - Add commandPrefix to vars from overlay settings - Add commandPrefixedName to buildCommandVars - Add 16 unit + integration tests (all pass, 93 existing tests unaffected) Default is null (no prefix) for full backwards compatibility. https://claude.ai/code/session_01EBjmVEhi7fP2huAL3SBR6p * fix(sync): address review findings for command prefix - Remove unused afterAll import from test file - Add clarifying comment that non-spec command files are also prefixed - Add 2 integration tests verifying commandPrefixedName template variable renders correctly with and without prefix https://claude.ai/code/session_01EBjmVEhi7fP2huAL3SBR6p --------- Co-authored-by: Claude <noreply@anthropic.com> * fix(ci): CI remediation — package manager, review findings, test stability (#390) * fix(ci): resolve 7 bugs from project review - BUG-001: Replace flaky discover test with controlled temp fixture - BUG-002: Run prettier --write to fix formatting drift - BUG-003: Add form-template detection skip in issue label validation - BUG-005: Change claude.yml to self-hosted runner - BUG-006: Align branch protection required status checks with project.yaml - BUG-007: Fix command injection in resolve-merge.sh (use grep -F) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * docs: update changelog, add planning registry review findings - Add changelog entries for Wave 1-3 fixes (Added/Changed/Fixed/Removed) - Add Project Review Findings section to planning registry (PR-001 to PR-014) - Update planning docs after sync merge Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(review): add --generate-plans flag to project-review command Add Phase 2.5 plan generation after project review findings. When --generate-plans is passed (default: true), scaffold plan files from critical/high findings into docs/planning/review-findings/. Also includes sync cleanup of stale cursor/windsurf settings. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore(sync): regenerate all outputs after project review fixes Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(cli): dynamic flag loading from commands.yaml + context-aware template hook - Replace ~200 lines of hardcoded VALID_FLAGS/FLAG_TYPES with loadCommandFlags() that reads flag definitions from commands.yaml at startup - CLI_INTERNAL_FLAGS/CLI_INTERNAL_FLAG_TYPES cover commands not in commands.yaml - Self-validation warns at startup if any flag is missing a type definition - Update cli.test.mjs to validate CLI_INTERNAL_FLAGS consistency - Fix scaffold-once orphan bug: carry forward manifest entries for files skipped by scaffold-once so orphan cleanup does not delete them - Make protect-templates hook context-aware: skip protection in the agentkit-forge source repo (detected via package.json name) so maintainer agents can edit templates; block only in downstream repos Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(sync): add managed-mode script templates for downstream repos Add 14 script templates (.agentkit/templates/scripts/) with `managed` scaffold mode so downstream repos receive script updates via three-way merge while preserving local customizations. Templates include: create-doc, update-changelog, validate-documentation, validate-numbering, check-documentation-requirement, sync-issues, sync-split-pr, setup-agentkit-branch-governance, and resolve-merge (both .sh and .ps1 variants where applicable). Parameterized templates use {{defaultBranch}} and branch protection variables from project.yaml. Engine wired via syncScripts() under doc-scaffolding feature gate. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(teams): add TeamForge meta-team for agent team creation (cogmesh #130) Add the TEAMFORGE meta-team (T11) — a structured pipeline for creating, validating, and deploying new agent team specifications. Adapted from cogmesh #130 with a simplified 6-agent pipeline: - input-clarifier: assess requests, extract constraints - mission-definer: lock team definition (ID, scope, accepts) - role-architect: design agent roles and dependencies - prompt-engineer: write agent descriptions and rules - flow-designer: design team command and integration points - team-validator: quality gate for spec consistency Includes /team-forge command with --task flag (create-team, validate-team, audit-teams, update-team) and planning doc. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(teams): add Strategic Ops team for cross-project coordination Add the STRATEGIC OPS team (T12) — handles framework governance, portfolio analysis, adoption strategy, impact assessment, and release coordination across all repos using AgentKit Forge. 5-agent pipeline: - portfolio-analyst: inventory repos, detect drift, adoption metrics - governance-advisor: versioning strategy, breaking change protocols - adoption-strategist: onboarding, migration paths, rollout plans - impact-assessor: blast radius analysis for template/spec changes - release-coordinator: version bumps, sync waves, release comms Includes /team-strategic-ops command with --task and --scope flags. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(agents): add agent/team relationship matrix analysis engine + scripts Add comprehensive agent/team relationship analysis with 8 cross-reference matrices and 10 supplementary analyses (orphans, cycles, bottlenecks, reachability, critical path, notification amplifiers, etc.). - Fix YAML structure: strategic-ops agents now under own top-level key - Add explicit agents: lists to forge + strategic-ops teams in teams.yaml - Add consolidation detection responsibilities to portfolio-analyst - Create agent-analysis.mjs engine module (loadFullAgentGraph + renderers) - Wire analyze-agents CLI command with --output/--matrix/--format flags - Add managed-scaffold script templates (bash + PowerShell) - Integrate into sync pipeline (auto-regenerates matrix on spec changes) - Add 33 tests covering all matrices, analyses, and edge cases Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: update documentation files and add plan template - Add trailing newlines to Cursor command documentation files for consistency - Add new plan template files for project planning - Improve markdown table formatting in Claude skills documentation - Remove obsolete .clinerules/testing.md file - Update various rule files with better formatting and advisory rule alignment * feat(agents): add spec-compliance-auditor feedback loop + Cost Ops team (T14) - Add spec-compliance-auditor to operations category (quality team) — closes the feedback loop between agent specs and actual behavior - Add Cost Ops team (T14) with 5 agents: model-economist, token-efficiency-engineer, vendor-arbitrage-analyst, grant-hunter, cost-ops-monitor - Add ai-cost-ops rules domain with 6 conventions (model routing, token budgets, caching, batch APIs, vendor abstraction, credit tracking) - Add team-cost-ops command with --task, --period, --provider flags - Update notification chains: data→cost-ops-monitor, infra→model-economist, retrospective-analyst→spec-compliance-auditor - Add intake routes: cost-ops, agent-performance Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(teams): add implement to cost-ops team accepts list Resolves agent/team accepts mismatch — token-efficiency-engineer accepts implement but the team definition only had investigate/review/plan/document. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(cost-ops): add multi-provider infra cost ticket to backlog Add detailed planning ticket for multi-provider infrastructure cost normalisation, routing, and cost-agent integration. Covers 9 providers (Anthropic, OpenAI, Google, Mistral, Cohere, self-hosted, Azure, AWS, GCP) with 3-phase delivery plan and cross-team dependency tracking. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(templates): resolve PR review comments from CodeRabbit - Fix protect-templates.sh: package name check uses correct "agentkit-forge-runtime" instead of "agentkit-forge" - Fix protect-templates.ps1: malformed path (missing separator before .agentkit) and same package name correction - Fix update-changelog.ps1: change .mjs to .cjs to match CommonJS require() syntax used in the inline Node script - Fix resolve-merge.sh: add fallback for {{defaultBranch}} placeholder - Fix AGENT_TEAMS.md: resolve three-way merge conflict markers left by sync engine, keeping user formatting + implement in cost-ops Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(cost-ops): add WebSearch/WebFetch tools to cost-ops agents Enable web research capabilities for cost-ops team: - Add WebSearch and WebFetch to /team-cost-ops allowed-tools - Add WebSearch and WebFetch to model-economist, vendor-arbitrage-analyst, and grant-hunter agent preferred-tools - Add web intake expansion ticket (P2) for MCP crawler, Puppeteer integration, automated pricing refresh, and cross-session persistence - Regenerate sync outputs Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(cost-ops): add Cost Ops team, agents, and multi-provider cost ticket (#364) * feat(agents): add spec-compliance-auditor feedback loop + Cost Ops team (T14) - Add spec-compliance-auditor to operations category (quality team) — closes the feedback loop between agent specs and actual behavior - Add Cost Ops team (T14) with 5 agents: model-economist, token-efficiency-engineer, vendor-arbitrage-analyst, grant-hunter, cost-ops-monitor - Add ai-cost-ops rules domain with 6 conventions (model routing, token budgets, caching, batch APIs, vendor abstraction, credit tracking) - Add team-cost-ops command with --task, --period, --provider flags - Update notification chains: data→cost-ops-monitor, infra→model-economist, retrospective-analyst→spec-compliance-auditor - Add intake routes: cost-ops, agent-performance Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(teams): add implement to cost-ops team accepts list Resolves agent/team accepts mismatch — token-efficiency-engineer accepts implement but the team definition only had investigate/review/plan/document. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(cost-ops): add multi-provider infra cost ticket to backlog Add detailed planning ticket for multi-provider infrastructure cost normalisation, routing, and cost-agent integration. Covers 9 providers (Anthropic, OpenAI, Google, Mistral, Cohere, self-hosted, Azure, AWS, GCP) with 3-phase delivery plan and cross-team dependency tracking. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(templates): resolve PR review comments from CodeRabbit - Fix protect-templates.sh: package name check uses correct "agentkit-forge-runtime" instead of "agentkit-forge" - Fix protect-templates.ps1: malformed path (missing separator before .agentkit) and same package name correction - Fix update-changelog.ps1: change .mjs to .cjs to match CommonJS require() syntax used in the inline Node script - Fix resolve-merge.sh: add fallback for {{defaultBranch}} placeholder - Fix AGENT_TEAMS.md: resolve three-way merge conflict markers left by sync engine, keeping user formatting + implement in cost-ops Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(cost-ops): add WebSearch/WebFetch tools to cost-ops agents (#365) Enable web research capabilities for cost-ops team: - Add WebSearch and WebFetch to /team-cost-ops allowed-tools - Add WebSearch and WebFetch to model-economist, vendor-arbitrage-analyst, and grant-hunter agent preferred-tools - Add web intake expansion ticket (P2) for MCP crawler, Puppeteer integration, automated pricing refresh, and cross-session persistence - Regenerate sync outputs Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> * fix(teams): address CodeRabbit review findings on strategic-ops PR - Lazy-load js-yaml in cli.mjs after ensureDependencies() to prevent crash when node_modules is missing - Convert YAML frontmatter to PowerShell comment blocks in all 6 PS1 templates to fix invalid PowerShell syntax - Fix protect-templates hook path: use 3 parent traversals to reach .agentkit/package.json from hooks directory - Remove schema-invalid 'phase' field from ai-cost-ops rule domain - Narrow strategic-ops scope: replace **/* catch-all with specific files - Add strategic-ops to cost-ops handoff-chain for consistency - Add Write tool to spec-compliance-auditor, vendor-arbitrage-analyst, and grant-hunter agents - Fix glob matching in resolve-merge.sh (use regex instead of broken sed strip) - Add merge failure vs conflict detection in resolve-merge.ps1 - Add branch existence check in setup-agentkit-branch-governance scripts - Add gh CLI preflight check in sync-split-pr.ps1 - Deduplicate branch protection loop when defaultBranch is 'main' - Fix applies-to glob: docs/planning/cost/** → docs/planning/cost-governance/** - Fix non-canonical doc paths in intake-agent-proposal.md - Add changelog entries for new teams, agents, and analysis engine - Resolve AGENT_TEAMS.md merge conflict (accept narrowed scope) - Run prettier on all modified files Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(templates): add gh auth preflight and changelog divider handling - sync-split-pr.ps1: add gh auth status check before side effects - update-changelog.ps1: stop before --- divider when appending entries Addresses CodeRabbit review comments #7 and #13 on PR #356. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(sync): set executable permission on analyze-agents.sh Linux CI sync produces +x permissions; align local to match. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(templates): address CodeRabbit review round 3-4 findings - Fix YAML frontmatter in copilot agent template: use double quotes for description field to handle apostrophes (CRITICAL) - Fix protect-templates.sh/ps1 path traversal: correct parent directory count for .agentkit/package.json source repo detection - Add $PSNativeCommandUseErrorActionPreference to sync-split-pr.ps1 so native command failures (git, pnpm, gh) are treated as fatal - Replace try/catch with $LASTEXITCODE check for gh auth status - Deduplicate branch loop in setup-agentkit-branch-governance.sh when defaultBranch equals 'main' - Fix duplicate verification echo lines in governance scripts Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * style(docs): fix prettier formatting on planning documents Run prettier --write on web-intake-expansion.md and intake-agent-proposal.md to fix CI formatting check. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(tests): isolate render target gating tests with fresh temp dirs Tests in the "render target gating" describe block shared a single temp directory via beforeAll/afterAll. The first test ran --only claude (generating .claude/ files), and the second ran --only warp expecting no Claude files — but leftovers from test 1 caused the assertion to fail. Changing to beforeEach/afterEach gives each test a clean directory. Closes #377 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(commands): add /start command as new user entry point Adds a context-aware triage command that detects repository state (fresh clone, post-discovery, mid-session, uncommitted work) and guides users to the right command or team for their goal. Includes team routing table, 4 contextual flows, and decision guidance for when users don't know which team to use. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * refactor(commands): add Arguments and State Management sections to /start Addresses TEAMFORGE validation findings: - Add dedicated Arguments section documenting $ARGUMENTS handling - Add State Management section (reads/writes inventory) - Fix frontmatter: remove misleading generated_by field - Add explicit "manually authored" comment header https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): add /start to spec and template for cross-repo generation Moves /start from a hand-authored command to a proper spec-driven, sync-generated command available to any repo that adopts AgentKit Forge. - Add start command definition to commands.yaml (no feature gate — always on) - Create start.md template in .agentkit/templates/claude/commands/ - Add /start to CLAUDE.md Quick Reference table template https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after adding /start command Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): make /start team routing dynamic instead of hardcoded Replace the static team routing table with dynamic discovery: 1. Read AGENT_TEAMS.md (from /discover) at runtime 2. Fall back to .agentkit/spec/teams.yaml 3. Fall back to /team-* command frontmatter This ensures /start always reflects the actual teams configured in any repo, rather than a hardcoded list that could go stale. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after dynamic routing change Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add interactive TUI entry point with hybrid UI Replace static markdown output with an ink-based terminal UI that combines two modes: a guided conversation flow for first-run users and a fuzzy-searchable command palette for returning users. A persistent status bar shows repo state at a glance (branch, phase, backlog count, working tree status). - Context detection module mirrors /start Phase 1 signals - ConversationFlow: branching dialogue tree (choose-your-own-adventure) - CommandPalette: fuzzy search with context-ranked star recommendations - StatusBar: tmux-style persistent strip with color-coded segments - Supports --json flag for scripting/piping https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add test suite, error handling, and refactor for production readiness - Add vitest test infrastructure with 102 tests across 7 files - Coverage: 95.58% statements, 90.81% branches, 96.72% functions - Extract conversation tree to separate config module for testability - Add error boundary to App component for graceful error display - Add --help flag with usage documentation - Add TTY detection with JSON fallback for non-interactive environments - Add SIGINT/SIGTERM signal handling for clean exit https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore: add coverage to gitignore, include plan and workspace config https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — unused code, git cwd, magic numbers - Call exit() after command selection so Ink process terminates - Remove unused ctx prop from Header component - Fix git commands to use -C flag with root path parameter - Extract dumpContextJson() helper to deduplicate JSON output logic - Add comment explaining hardcoded team filter exclusion - Replace magic numbers with named constants (FUSE_THRESHOLD, RECOMMENDED_SCORE, MAX_BRANCH_LENGTH) - Remove unused ink-spinner dependency - Add test verifying git -C flag passes root correctly https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — security, correctness, test quality - CRITICAL: Replace execSync shell interpolation with execFileSync to prevent command injection via root parameter in detect.js - CRITICAL: Remove phantom --external:ink-spinner from build script and switch npx to direct esbuild invocation - HIGH: Fix exit race condition — use useEffect instead of setTimeout - HIGH: Wire up onSelect callback in ConversationFlow so Guide mode triggers the result screen in App - HIGH: Destructure and accept ctx prop in ConversationFlow - HIGH: Add back-navigation (Escape) in ConversationFlow - HIGH: Guard against undefined team.focus in commands.js tags - MEDIUM: Use functional setCursor form to avoid stale closures - MEDIUM: Key commandIndices Map by string id instead of object identity - MEDIUM: Improve parseTeams header detection (drop first row approach) - MEDIUM: Filter completed/done/closed items from backlogCount - MEDIUM: Extract shared makeCtx test utility across all test files - MEDIUM: Add null guard to StatusBar truncate helper - LOW: Validate orchestratorPhase is a number in range 1-5 - LOW: Fix pnpm-workspace.yaml list syntax - Replace all setTimeout in tests with vi.waitFor deterministic waits https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(engine): add pre-sync commit guard and interactive apply mode Adds two safety features to the sync pipeline: 1. Pre-sync commit guard: Detects uncommitted changes in protected directories (.agentkit/engines, spec, overlays) before sync runs. In TTY mode, prompts to abort, stash, or continue. In non-TTY mode (CI), prints a warning and proceeds. 2. Interactive apply mode: After rendering, shows a change summary and prompts: apply all / skip all / prompt each file. Per-file prompt supports show-diff and apply-all-remaining. Default in TTY; bypassed with --yes, --no-prompt, or --force. New module: sync-guard.mjs with 4 exported functions and 7 tests. New CLI flags: --yes, --no-prompt for non-interactive sync. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore(sync): regenerate outputs after branch merges Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore(sync): regenerate outputs after merge of new-user-entry-point Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(engine): add configurable package manager and fix review findings - Add `stack.packageManager` field to project.yaml (pnpm | npm | yarn) - Derive helper template vars (pmInstall, pmRun, pmExec, pmLockfile, etc.) - Update CLAUDE.md template and hook/workflow templates to use {{packageManager}} - Fix sync-guard to exclude .agentkit/spec from protected dirs and add try/catch - Remove duplicate cost-ops team definition from teams.yaml - Pin all dependency versions in package.json (remove ^ prefixes) - Add vitest coverage thresholds (80% statements/branches/functions/lines) - Fix src/start/ code quality: null guards, exit delay, error boundaries - Harden consolidate-branches.sh: self-resolution guard, stash restore - Regenerate all 533 output files via agentkit sync Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore(engine): add brand color palette variables to sync vars Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(ci): fix test race condition, workspace config, and lockfile - Fix ConversationFlow test: wait for 'Got it' before asserting hint text - Add packages field to pnpm-workspace.yaml for proper workspace resolution - Regenerate lockfile after version pinning (removed ^ prefixes) - Remove accidental .agentkit/templates/src/ artifacts Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(start): add event loop yields to ConversationFlow tests ink-select-input needs setImmediate yields after a new menu renders before it can process ENTER keypresses. Without this, the second ENTER in leaf-selection tests was swallowed, causing intermittent failures. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> * fix(spec): correct githubSlug to phoenixvc/agentkit-forge (#391) Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> * Add entry point for new framework users (#389) * feat(commands): add /start command as new user entry point Adds a context-aware triage command that detects repository state (fresh clone, post-discovery, mid-session, uncommitted work) and guides users to the right command or team for their goal. Includes team routing table, 4 contextual flows, and decision guidance for when users don't know which team to use. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * refactor(commands): add Arguments and State Management sections to /start Addresses TEAMFORGE validation findings: - Add dedicated Arguments section documenting $ARGUMENTS handling - Add State Management section (reads/writes inventory) - Fix frontmatter: remove misleading generated_by field - Add explicit "manually authored" comment header https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): add /start to spec and template for cross-repo generation Moves /start from a hand-authored command to a proper spec-driven, sync-generated command available to any repo that adopts AgentKit Forge. - Add start command definition to commands.yaml (no feature gate — always on) - Create start.md template in .agentkit/templates/claude/commands/ - Add /start to CLAUDE.md Quick Reference table template https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after adding /start command Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): make /start team routing dynamic instead of hardcoded Replace the static team routing table with dynamic discovery: 1. Read AGENT_TEAMS.md (from /discover) at runtime 2. Fall back to .agentkit/spec/teams.yaml 3. Fall back to /team-* command frontmatter This ensures /start always reflects the actual teams configured in any repo, rather than a hardcoded list that could go stale. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after dynamic routing change Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add interactive TUI entry point with hybrid UI Replace static markdown output with an ink-based terminal UI that combines two modes: a guided conversation flow for first-run users and a fuzzy-searchable command palette for returning users. A persistent status bar shows repo state at a glance (branch, phase, backlog count, working tree status). - Context detection module mirrors /start Phase 1 signals - ConversationFlow: branching dialogue tree (choose-your-own-adventure) - CommandPalette: fuzzy search with context-ranked star recommendations - StatusBar: tmux-style persistent strip with color-coded segments - Supports --json flag for scripting/piping https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add test suite, error handling, and refactor for production readiness - Add vitest test infrastructure with 102 tests across 7 files - Coverage: 95.58% statements, 90.81% branches, 96.72% functions - Extract conversation tree to separate config module for testability - Add error boundary to App component for graceful error display - Add --help flag with usage documentation - Add TTY detection with JSON fallback for non-interactive environments - Add SIGINT/SIGTERM signal handling for clean exit https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore: add coverage to gitignore, include plan and workspace config https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — unused code, git cwd, magic numbers - Call exit() after command selection so Ink process terminates - Remove unused ctx prop from Header component - Fix git commands to use -C flag with root path parameter - Extract dumpContextJson() helper to deduplicate JSON output logic - Add comment explaining hardcoded team filter exclusion - Replace magic numbers with named constants (FUSE_THRESHOLD, RECOMMENDED_SCORE, MAX_BRANCH_LENGTH) - Remove unused ink-spinner dependency - Add test verifying git -C flag passes root correctly https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — security, correctness, test quality - CRITICAL: Replace execSync shell interpolation with execFileSync to prevent command injection via root parameter in detect.js - CRITICAL: Remove phantom --external:ink-spinner from build script and switch npx to direct esbuild invocation - HIGH: Fix exit race condition — use useEffect instead of setTimeout - HIGH: Wire up onSelect callback in ConversationFlow so Guide mode triggers the result screen in App - HIGH: Destructure and accept ctx prop in ConversationFlow - HIGH: Add back-navigation (Escape) in ConversationFlow - HIGH: Guard against undefined team.focus in commands.js tags - MEDIUM: Use functional setCursor form to avoid stale closures - MEDIUM: Key commandIndices Map by string id instead of object identity - MEDIUM: Improve parseTeams header detection (drop first row approach) - MEDIUM: Filter completed/done/closed items from backlogCount - MEDIUM: Extract shared makeCtx test utility across all test files - MEDIUM: Add null guard to StatusBar truncate helper - LOW: Validate orchestratorPhase is a number in range 1-5 - LOW: Fix pnpm-workspace.yaml list syntax - Replace all setTimeout in tests with vi.waitFor deterministic waits https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * test(start): add coverage for result screen exit path Add App-level test that navigates through ConversationFlow to a leaf node and verifies the result screen text is rendered before exit(). Confirms the synchronous useEffect exit is safe — React commits the render (Ink captures the frame) before useEffect fires. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore: update generated sync output timestamps Generated files updated with current sync date from dev merge. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW --------- Co-authored-by: Claude <noreply@anthropic.com> * fix: caldues heuristics (#398) * feat: complete revisit of agents (#399) (#400) * Add start command: new user entry point with state detection (#387) * fix(commands): add AskUserQuestion to VALID_TOOLS and /start command The /start command session got stuck because AskUserQuestion was not included in the allowed-tools whitelist. This fix addresses three issues: 1. VALID_TOOLS in spec-validator was missing AskUserQuestion, TodoWrite, Agent, and NotebookEdit — preventing commands from declaring these Claude Code built-in tools in their allowed-tools. 2. The /start command template now explicitly includes AskUserQuestion in its allowed-tools frontmatter and instructs the agent to use it for interactive guided choices (Phase 3). 3. Added /start command spec to commands.yaml with AskUserQuestion as a declared tool dependency. Also adds a test case validating all four newly-added tools are accepted by the spec validator. https://claude.ai/code/session_01Qh3Xk3jFkVdeRAXTqLvq3M * fix(commands): remove unrendered Handlebars comment from start.md output The generated .claude/commands/start.md contained a raw {{! ... }} Handlebars comment that was not processed by the sync engine. Remove it so the generated output is clean Markdown. https://claude.ai/code/session_01Qh3Xk3jFkVdeRAXTqLvq3M --------- * Add configurable prefix to kits commands (#388) * feat(sync): add configurable command prefix for generated slash commands Add `commandPrefix` setting to overlay settings that namespaces all generated slash commands across platforms: - Claude Code: subdirectory strategy (kits/check.md → /project:kits:check) - Cursor/Windsurf/Copilot/Codex: filename prefix (kits-check.md → /kits-check) - Team commands excluded from prefixing (already namespaced) Changes: - Add resolveCommandPath() helper with subdirectory/filename strategies - Update syncClaudeCommands, syncClaudeSkills, syncCursorCommands, syncWindsurfCommands, syncCopilotPrompts, syncCodexSkills - Add commandPrefix to vars from overlay settings - Add commandPrefixedName to buildCommandVars - Add 16 unit + integration tests (all pass, 93 existing tests unaffected) Default is null (no prefix) for full backwards compatibility. https://claude.ai/code/session_01EBjmVEhi7fP2huAL3SBR6p * fix(sync): address review findings for command prefix - Remove unused afterAll import from test file - Add clarifying comment that non-spec command files are also prefixed - Add 2 integration tests verifying commandPrefixedName template variable renders correctly with and without prefix https://claude.ai/code/session_01EBjmVEhi7fP2huAL3SBR6p --------- * fix(ci): CI remediation — package manager, review findings, test stability (#390) * fix(ci): resolve 7 bugs from project review - BUG-001: Replace flaky discover test with controlled temp fixture - BUG-002: Run prettier --write to fix formatting drift - BUG-003: Add form-template detection skip in issue label validation - BUG-005: Change claude.yml to self-hosted runner - BUG-006: Align branch protection required status checks with project.yaml - BUG-007: Fix command injection in resolve-merge.sh (use grep -F) * docs: update changelog, add planning registry review findings - Add changelog entries for Wave 1-3 fixes (Added/Changed/Fixed/Removed) - Add Project Review Findings section to planning registry (PR-001 to PR-014) - Update planning docs after sync merge * feat(review): add --generate-plans flag to project-review command Add Phase 2.5 plan generation after project review findings. When --generate-plans is passed (default: true), scaffold plan files from critical/high findings into docs/planning/review-findings/. Also includes sync cleanup of stale cursor/windsurf settings. * chore(sync): regenerate all outputs after project review fixes * feat(cli): dynamic flag loading from commands.yaml + context-aware template hook - Replace ~200 lines of hardcoded VALID_FLAGS/FLAG_TYPES with loadCommandFlags() that reads flag definitions from commands.yaml at startup - CLI_INTERNAL_FLAGS/CLI_INTERNAL_FLAG_TYPES cover commands not in commands.yaml - Self-validation warns at startup if any flag is missing a type definition - Update cli.test.mjs to validate CLI_INTERNAL_FLAGS consistency - Fix scaffold-once orphan bug: carry forward manifest entries for files skipped by scaffold-once so orphan cleanup does not delete them - Make protect-templates hook context-aware: skip protection in the agentkit-forge source repo (detected via package.json name) so maintainer agents can edit templates; block only in downstream repos * feat(sync): add managed-mode script templates for downstream repos Add 14 script templates (.agentkit/templates/scripts/) with `managed` scaffold mode so downstream repos receive script updates via three-way merge while preserving local customizations. Templates include: create-doc, update-changelog, validate-documentation, validate-numbering, check-documentation-requirement, sync-issues, sync-split-pr, setup-agentkit-branch-governance, and resolve-merge (both .sh and .ps1 variants where applicable). Parameterized templates use {{defaultBranch}} and branch protection variables from project.yaml. Engine wired via syncScripts() under doc-scaffolding feature gate. * feat(teams): add TeamForge meta-team for agent team creation (cogmesh #130) Add the TEAMFORGE meta-team (T11) — a structured pipeline for creating, validating, and deploying new agent team specifications. Adapted from cogmesh #130 with a simplified 6-agent pipeline: - input-clarifier: assess requests, extract constraints - mission-definer: lock team definition (ID, scope, accepts) - role-architect: design agent roles and dependencies - prompt-engineer: write agent descriptions and rules - flow-designer: design team command and integration points - team-validator: quality gate for spec consistency Includes /team-forge command with --task flag (create-team, validate-team, audit-teams, update-team) and planning doc. * feat(teams): add Strategic Ops team for cross-project coordination Add the STRATEGIC OPS team (T12) — handles framework governance, portfolio analysis, adoption strategy, impact assessment, and release coordination across all repos using AgentKit Forge. 5-agent pipeline: - portfolio-analyst: inventory repos, detect drift, adoption metrics - governance-advisor: versioning strategy, breaking change protocols - adoption-strategist: onboarding, migration paths, rollout plans - impact-assessor: blast radius analysis for template/spec changes - release-coordinator: version bumps, sync waves, release comms Includes /team-strategic-ops command with --task and --scope flags. * feat(agents): add agent/team relationship matrix analysis engine + scripts Add comprehensive agent/team relationship analysis with 8 cross-reference matrices and 10 supplementary analyses (orphans, cycles, bottlenecks, reachability, critical path, notification amplifiers, etc.). - Fix YAML structure: strategic-ops agents now under own top-level key - Add explicit agents: lists to forge + strategic-ops teams in teams.yaml - Add consolidation detection responsibilities to portfolio-analyst - Create agent-analysis.mjs engine module (loadFullAgentGraph + renderers) - Wire analyze-agents CLI command with --output/--matrix/--format flags - Add managed-scaffold script templates (bash + PowerShell) - Integrate into sync pipeline (auto-regenerates matrix on spec changes) - Add 33 tests covering all matrices, analyses, and edge cases * chore: update documentation files and add plan template - Add trailing newlines to Cursor command documentation files for consistency - Add new plan template files for project planning - Improve markdown table formatting in Claude skills documentation - Remove obsolete .clinerules/testing.md file - Update various rule files with better formatting and advisory rule alignment * feat(agents): add spec-compliance-auditor feedback loop + Cost Ops team (T14) - Add spec-compliance-auditor to operations category (quality team) — closes the feedback loop between agent specs and actual behavior - Add Cost Ops team (T14) with 5 agents: model-economist, token-efficiency-engineer, vendor-arbitrage-analyst, grant-hunter, cost-ops-monitor - Add ai-cost-ops rules domain with 6 conventions (model routing, token budgets, caching, batch APIs, vendor abstraction, credit tracking) - Add team-cost-ops command with --task, --period, --provider flags - Update notification chains: data→cost-ops-monitor, infra→model-economist, retrospective-analyst→spec-compliance-auditor - Add intake routes: cost-ops, agent-performance * fix(teams): add implement to cost-ops team accepts list Resolves agent/team accepts mismatch — token-efficiency-engineer accepts implement but the team definition only had investigate/review/plan/document. * feat(cost-ops): add multi-provider infra cost ticket to backlog Add detailed planning ticket for multi-provider infrastructure cost normalisation, routing, and cost-agent integration. Covers 9 providers (Anthropic, OpenAI, Google, Mistral, Cohere, self-hosted, Azure, AWS, GCP) with 3-phase delivery plan and cross-team dependency tracking. * fix(templates): resolve PR review comments from CodeRabbit - Fix protect-templates.sh: package name check uses correct "agentkit-forge-runtime" instead of "agentkit-forge" - Fix protect-templates.ps1: malformed path (missing separator before .agentkit) and same package name correction - Fix update-changelog.ps1: change .mjs to .cjs to match CommonJS require() syntax used in the inline Node script - Fix resolve-merge.sh: add fallback for {{defaultBranch}} placeholder - Fix AGENT_TEAMS.md: resolve three-way merge conflict markers left by sync engine, keeping user formatting + implement in cost-ops * feat(cost-ops): add WebSearch/WebFetch tools to cost-ops agents Enable web research capabilities for cost-ops team: - Add WebSearch and WebFetch to /team-cost-ops allowed-tools - Add WebSearch and WebFetch to model-economist, vendor-arbitrage-analyst, and grant-hunter agent preferred-tools - Add web intake expansion ticket (P2) for MCP crawler, Puppeteer integration, automated pricing refresh, and cross-session persistence - Regenerate sync outputs * feat(cost-ops): add Cost Ops team, agents, and multi-provider cost ticket (#364) * feat(agents): add spec-compliance-auditor feedback loop + Cost Ops team (T14) - Add spec-compliance-auditor to operations category (quality team) — closes the feedback loop between agent specs and actual behavior - Add Cost Ops team (T14) with 5 agents: model-economist, token-efficiency-engineer, vendor-arbitrage-analyst, grant-hunter, cost-ops-monitor - Add ai-cost-ops rules domain with 6 conventions (model routing, token budgets, caching, batch APIs, vendor abstraction, credit tracking) - Add team-cost-ops command with --task, --period, --provider flags - Update notification chains: data→cost-ops-monitor, infra→model-economist, retrospective-analyst→spec-compliance-auditor - Add intake routes: cost-ops, agent-performance * fix(teams): add implement to cost-ops team accepts list Resolves agent/team accepts mismatch — token-efficiency-engineer accepts implement but the team definition only had investigate/review/plan/document. * feat(cost-ops): add multi-provider infra cost ticket to backlog Add detailed planning ticket for multi-provider infrastructure cost normalisation, routing, and cost-agent integration. Covers 9 providers (Anthropic, OpenAI, Google, Mistral, Cohere, self-hosted, Azure, AWS, GCP) with 3-phase delivery plan and cross-team dependency tracking. * fix(templates): resolve PR review comments from CodeRabbit - Fix protect-templates.sh: package name check uses correct "agentkit-forge-runtime" instead of "agentkit-forge" - Fix protect-templates.ps1: malformed path (missing separator before .agentkit) and same package name correction - Fix update-changelog.ps1: change .mjs to .cjs to match CommonJS require() syntax used in the inline Node script - Fix resolve-merge.sh: add fallback for {{defaultBranch}} placeholder - Fix AGENT_TEAMS.md: resolve three-way merge conflict markers left by sync engine, keeping user formatting + implement in cost-ops * feat(cost-ops): add WebSearch/WebFetch tools to cost-ops agents (#365) Enable web research capabilities for cost-ops team: - Add WebSearch and WebFetch to /team-cost-ops allowed-tools - Add WebSearch and WebFetch to model-economist, vendor-arbitrage-analyst, and grant-hunter agent preferred-tools - Add web intake expansion ticket (P2) for MCP crawler, Puppeteer integration, automated pricing refresh, and cross-session persistence - Regenerate sync outputs --------- * fix(teams): address CodeRabbit review findings on strategic-ops PR - Lazy-load js-yaml in cli.mjs after ensureDependencies() to prevent crash when node_modules is missing - Convert YAML frontmatter to PowerShell comment blocks in all 6 PS1 templates to fix invalid PowerShell syntax - Fix protect-templates hook path: use 3 parent traversals to reach .agentkit/package.json from hooks directory - Remove schema-invalid 'phase' field from ai-cost-ops rule domain - Narrow strategic-ops scope: replace **/* catch-all with specific files - Add strategic-ops to cost-ops handoff-chain for consistency - Add Write tool to spec-compliance-auditor, vendor-arbitrage-analyst, and grant-hunter agents - Fix glob matching in resolve-merge.sh (use regex instead of broken sed strip) - Add merge failure vs conflict detection in resolve-merge.ps1 - Add branch existence check in setup-agentkit-branch-governance scripts - Add gh CLI preflight check in sync-split-pr.ps1 - Deduplicate branch protection loop when defaultBranch is 'main' - Fix applies-to glob: docs/planning/cost/** → docs/planning/cost-governance/** - Fix non-canonical doc paths in intake-agent-proposal.md - Add changelog entries for new teams, agents, and analysis engine - Resolve AGENT_TEAMS.md merge conflict (accept narrowed scope) - Run prettier on all modified files * fix(templates): add gh auth preflight and changelog divider handling - sync-split-pr.ps1: add gh auth status check before side effects - update-changelog.ps1: stop before --- divider when appending entries Addresses CodeRabbit review comments #7 and #13 on PR #356. * fix(sync): set executable permission on analyze-agents.sh Linux CI sync produces +x permissions; align local to match. * fix(templates): address CodeRabbit review round 3-4 findings - Fix YAML frontmatter in copilot agent template: use double quotes for description field to handle apostrophes (CRITICAL) - Fix protect-templates.sh/ps1 path traversal: correct parent directory count for .agentkit/package.json source repo detection - Add $PSNativeCommandUseErrorActionPreference to sync-split-pr.ps1 so native command failures (git, pnpm, gh) are treated as fatal - Replace try/catch with $LASTEXITCODE check for gh auth status - Deduplicate branch loop in setup-agentkit-branch-governance.sh when defaultBranch equals 'main' - Fix duplicate verification echo lines in governance scripts * style(docs): fix prettier formatting on planning documents Run prettier --write on web-intake-expansion.md and intake-agent-proposal.md to fix CI formatting check. * fix(tests): isolate render target gating tests with fresh temp dirs Tests in the "render target gating" describe block shared a single temp directory via beforeAll/afterAll. The first test ran --only claude (generating .claude/ files), and the second ran --only warp expecting no Claude files — but leftovers from test 1 caused the assertion to fail. Changing to beforeEach/afterEach gives each test a clean directory. Closes #377 * feat(commands): add /start command as new user entry point Adds a context-aware triage command that detects repository state (fresh clone, post-discovery, mid-session, uncommitted work) and guides users to the right command or team for their goal. Includes team routing table, 4 contextual flows, and decision guidance for when users don't know which team to use. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * refactor(commands): add Arguments and State Management sections to /start Addresses TEAMFORGE validation findings: - Add dedicated Arguments section documenting $ARGUMENTS handling - Add State Management section (reads/writes inventory) - Fix frontmatter: remove misleading generated_by field - Add explicit "manually authored" comment header https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): add /start to spec and template for cross-repo generation Moves /start from a hand-authored command to a proper spec-driven, sync-generated command available to any repo that adopts AgentKit Forge. - Add start command definition to commands.yaml (no feature gate — always on) - Create start.md template in .agentkit/templates/claude/commands/ - Add /start to CLAUDE.md Quick Reference table template https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after adding /start command Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): make /start team routing dynamic instead of hardcoded Replace the static team routing table with dynamic discovery: 1. Read AGENT_TEAMS.md (from /discover) at runtime 2. Fall back to .agentkit/spec/teams.yaml 3. Fall back to /team-* command frontmatter This ensures /start always reflects the actual teams configured in any repo, rather than a hardcoded list that could go stale. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after dynamic routing change Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add interactive TUI entry point with hybrid UI Replace static markdown output with an ink-based terminal UI that combines two modes: a guided conversation flow for first-run users and a fuzzy-searchable command palette for returning users. A persistent status bar shows repo state at a glance (branch, phase, backlog count, working tree status). - Context detection module mirrors /start Phase 1 signals - ConversationFlow: branching dialogue tree (choose-your-own-adventure) - CommandPalette: fuzzy search with context-ranked star recommendations - StatusBar: tmux-style persistent strip with color-coded segments - Supports --json flag for scripting/piping https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add test suite, error handling, and refactor for production readiness - Add vitest test infrastructure with 102 tests across 7 files - Coverage: 95.58% statements, 90.81% branches, 96.72% functions - Extract conversation tree to separate config module for testability - Add error boundary to App component for graceful error display - Add --help flag with usage documentation - Add TTY detection with JSON fallback for non-interactive environments - Add SIGINT/SIGTERM signal handling for clean exit https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore: add coverage to gitignore, include plan and workspace config https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — unused code, git cwd, magic numbers - Call exit() after command selection so Ink process terminates - Remove unused ctx prop from Header component - Fix git commands to use -C flag with root path parameter - Extract dumpContextJson() helper to deduplicate JSON output logic - Add comment explaining hardcoded team filter exclusion - Replace magic numbers with named constants (FUSE_THRESHOLD, RECOMMENDED_SCORE, MAX_BRANCH_LENGTH) - Remove unused ink-spinner dependency - Add test verifying git -C flag passes root correctly https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — security, correctness, test quality - CRITICAL: Replace execSync shell interpolation with execFileSync to prevent command injection via root parameter in detect.js - CRITICAL: Remove phantom --external:ink-spinner from build script and switch npx to direct esbuild invocation - HIGH: Fix exit race condition — use useEffect instead of setTimeout - HIGH: Wire up onSelect callback in ConversationFlow so Guide mode triggers the result screen in App - HIGH: Destructure and accept ctx prop in ConversationFlow - HIGH: Add back-navigation (Escape) in ConversationFlow - HIGH: Guard against undefined team.focus in commands.js tags - MEDIUM: Use functional setCursor form to avoid stale closures - MEDIUM: Key commandIndices Map by string id instead of object identity - MEDIUM: Improve parseTeams header detection (drop first row approach) - MEDIUM: Filter completed/done/closed items from backlogCount - MEDIUM: Extract shared makeCtx test utility across all test files - MEDIUM: Add null guard to StatusBar truncate helper - LOW: Validate orchestratorPhase is a number in range 1-5 - LOW: Fix pnpm-workspace.yaml list syntax - Replace all setTimeout in tests with vi.waitFor deterministic waits https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(engine): add pre-sync commit guard and interactive apply mode Adds two safety features to the sync pipeline: 1. Pre-sync commit guard: Detects uncommitted changes in protected directories (.agentkit/engines, spec, overlays) before sync runs. In TTY mode, prompts to abort, stash, or continue. In non-TTY mode (CI), prints a warning and proceeds. 2. Interactive apply mode: After rendering, shows a change summary and prompts: apply all / skip all / prompt each file. Per-file prompt supports show-diff and apply-all-remaining. Default in TTY; bypassed with --yes, --no-prompt, or --force. New module: sync-guard.mjs with 4 exported functions and 7 tests. New CLI flags: --yes, --no-prompt for non-interactive sync. * chore(sync): regenerate outputs after branch merges * chore(sync): regenerate outputs after merge of new-user-entry-point * feat(engine): add configurable package manager and fix review findings - Add `stack.packageManager` field to project.yaml (pnpm | npm | yarn) - Derive helper template vars (pmInstall, pmRun, pmExec, pmLockfile, etc.) - Update CLAUDE.md template and hook/workflow templates to use {{packageManager}} - Fix sync-guard to exclude .agentkit/spec from protected dirs and add try/catch - Remove duplicate cost-ops team definition from teams.yaml - Pin all dependency versions in package.json (remove ^ prefixes) - Add vitest coverage thresholds (80% statements/branches/functions/lines) - Fix src/start/ code quality: null guards, exit delay, error boundaries - Harden consolidate-branches.sh: self-resolution guard, stash restore - Regenerate all 533 output files via agentkit sync * chore(engine): add brand color palette variables to sync vars * fix(ci): fix test race condition, workspace config, and lockfile - Fix ConversationFlow test: wait for 'Got it' before asserting hint text - Add packages field to pnpm-workspace.yaml for proper workspace resolution - Regenerate lockfile after version pinning (removed ^ prefixes) - Remove accidental .agentkit/templates/src/ artifacts * fix(start): add event loop yields to ConversationFlow tests ink-select-input needs setImmediate yields after a new menu renders before it can process ENTER keypresses. Without this, the second ENTER in leaf-selection tests was swallowed, causing intermittent failures. --------- * fix(spec): correct githubSlug to phoenixvc/agentkit-forge (#391) * Add entry point for new framework users (#389) * feat(commands): add /start command as new user entry point Adds a context-aware triage command that detects repository state (fresh clone, post-discovery, mid-session, uncommitted work) and guides users to the right command or team for their goal. Includes team routing table, 4 contextual flows, and decision guidance for when users don't know which team to use. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * refactor(commands): add Arguments and State Management sections to /start Addresses TEAMFORGE validation findings: - Add dedicated Arguments section documenting $ARGUMENTS handling - Add State Management section (reads/writes inventory) - Fix frontmatter: remove misleading generated_by field - Add explicit "manually authored" comment header https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): add /start to spec and template for cross-repo generation Moves /start from a hand-authored command to a proper spec-driven, sync-generated command available to any repo that adopts AgentKit Forge. - Add start command definition to commands.yaml (no feature gate — always on) - Create start.md template in .agentkit/templates/claude/commands/ - Add /start to CLAUDE.md Quick Reference table template https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after adding /start command Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): make /start team routing dynamic instead of hardcoded Replace the static team routing table with dynamic discovery: 1. Read AGENT_TEAMS.md (from /discover) at runtime 2. Fall back to .agentkit/spec/teams.yaml 3. Fall back to /team-* command frontmatter This ensures /start always reflects the actual teams configured in any repo, rather than a hardcoded list that could go stale. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after dynamic routing change Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add interactive TUI entry point with hybrid UI Replace static markdown output with an ink-based terminal UI that combines two modes: a guided conversation flow for first-run users and a fuzzy-searchable command palette for returning users. A persistent status bar shows repo state at a glance (branch, phase, backlog count, working tree status). - Context detection module mirrors /start Phase 1 signals - ConversationFlow: branching dialogue tree (choose-your-own-adventure) - CommandPalette: fuzzy search with context-ranked star recommendations - StatusBar: tmux-style persistent strip with color-coded segments - Supports --json flag for scripting/piping https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add test suite, error handling, and refactor for production readiness - Add vitest test infrastructure with 102 tests across 7 files - Coverage: 95.58% statements, 90.81% branches, 96.72% functions - Extract conversation tree to separate config module for testability - Add error boundary to App component for graceful error display - Add --help flag with usage documentation - Add TTY detection with JSON fallback for non-interactive environments - Add SIGINT/SIGTERM signal handling for clean exit https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore: add coverage to gitignore, include plan and workspace config https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — unused code, git cwd, magic numbers - Call exit() after command selection so Ink process terminates - Remove unused ctx prop from Header component - Fix git commands to use -C flag with root path parameter - Extract dumpContextJson() helper to deduplicate JSON output logic - Add comment explaining hardcoded team filter exclusion - Replace magic numbers with named constants (FUSE_THRESHOLD, RECOMMENDED_SCORE, MAX_BRANCH_LENGTH) - Remove unused ink-spinner dependency - Add test verifying git -C flag passes root correctly https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — security, correctness, test quality - CRITICAL: Replace execSync shell interpolation with execFileSync to prevent command injection via root parameter in detect.js - CRITICAL: Remove phantom --external:ink-spinner from build script and switch npx to direct esbuild invocation - HIGH: Fix exit race condition — use useEffect instead of setTimeout - HIGH: Wire up onSelect callback in ConversationFlow so Guide mode triggers the result screen in App - HIGH: Destructure and accept ctx prop in ConversationFlow - HIGH: Add back-navigation (Escape) in ConversationFlow - HIGH: Guard against undefined team.focus in commands.js tags - MEDIUM: Use functional setCursor form to avoid stale closures - MEDIUM: Key commandIndices Map by string id instead of object identity - MEDIUM: Improve parseTeams header detection (drop first row approach) - MEDIUM: Filter completed/done/closed items from backlogCount - MEDIUM: Extract shared makeCtx test utility across all test files - MEDIUM: Add null guard to StatusBar truncate helper - LOW: Validate orchestratorPhase is a number in range 1-5 - LOW: Fix pnpm-workspace.yaml list syntax - Replace all setTimeout in tests with vi.waitFor deterministic waits https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * test(start): add coverage for result screen exit path Add App-level test that navigates through ConversationFlow to a leaf node and verifies the result screen text is rendered before exit(). Confirms the synchronous useEffect exit is safe — React commits the render (Ink captures the frame) before useEffect fires. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore: update generated sync output timestamps Generated files updated with current sync date from dev merge. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW --------- * fix: caldues heuristics (#398) --------- Co-authored-by: Claude <noreply@anthropic.com> * fix(quality): resolve all lint and format errors - Fix Prettier formatting across engine src and start components - Resolve 381 markdown lint errors (MD040, MD024, MD036, MD029, MD022, MD001) - Add markdownlint config rules for intentional doc patterns - Add .claude/worktrees to prettierignore to exclude external branches - Enable markdownlint MD024/MD026 for duplicate headings and trailing colons All quality checks now pass: Prettier (0 errors), Markdown lint (0 errors), Tests (111/111), Build (28.9kb) * I'll update the last_updated field in all the files from '2026-03-12' to '2026-03-13'. This appears to be a routine timestamp update across all the AgentKit Forge generated files. * docs: add AgentKit Forge sync feedback Add detailed feedback on AgentKit Forge v3.1.0 integration, focusing on: - Windows line-ending issues and multi-editor sync behavior - Documentation scaffold-once limitations and override challenges - Unresolved placeholder warnings lacking diagnostics - Windows-specific pnpm execution problems * docs: update CLAUDE.md with repository-specific editing guidelines Clarified that modifications to `.agentkit` files are permitted in the agentkit-forge repository, while upstream directories remain protected. This ensures users understand the editing boundaries for project configuration and template files. * docs(claude): allow .agentkit edits in this repo (NB for framework dev) Made-with: Cursor * chore(sync): regenerate outputs after agentkit:sync Made-with: Cursor --------- Co-authored-by: Claude <noreply@anthropic.com> * chore(sync): regenerate outputs and update timestamps (#429) * Add start command: new user entry point with state detection (#387) * fix(commands): add AskUserQuestion to VALID_TOOLS and /start command The /start command session got stuck because AskUserQuestion was not included in the allowed-tools whitelist. This fix addresses three issues: 1. VALID_TOOLS in spec-validator was missing AskUserQuestion, TodoWrite, Agent, and NotebookEdit — preventing commands from declaring these Claude Code built-in tools in their allowed-tools. 2. The /start command template now explicitly includes AskUserQuestion in its allowed-tools frontmatter and instructs the agent to use it for interactive guided choices (Phase 3). 3. Added /start command spec to commands.yaml with AskUserQuestion as a declared tool dependency. Also adds a test case validating all four newly-added tools are accepted by the spec validator. https://claude.ai/code/session_01Qh3Xk3jFkVdeRAXTqLvq3M * fix(commands): remove unrendered Handlebars comment from start.md output The generated .claude/commands/start.md contained a raw {{! ... }} Handlebars comment that was not processed by the sync engine. Remove it so the generated output is clean Markdown. https://claude.ai/code/session_01Qh3Xk3jFkVdeRAXTqLvq3M --------- Co-authored-by: Claude <noreply@anthropic.com> * Add configurable prefix to kits commands (#388) * feat(sync): add configurable command prefix for generated slash commands Add `commandPrefix` setting to overlay settings that namespaces all generated slash commands across platforms: - Claude Code: subdirectory strategy (kits/check.md → /project:kits:check) - Cursor/Windsurf/Copilot/Codex: filename prefix (kits-check.md → /kits-check) - Team commands excluded from prefixing (already namespaced) Changes: - Add resolveCommandPath() helper with subdirectory/filename strategies - Update syncClaudeCommands, syncClaudeSkills, syncCursorCommands, syncWindsurfCommands, syncCopilotPrompts…
…#432) * feat: new entry points (#426) * Add start command: new user entry point with state detection (#387) * fix(commands): add AskUserQuestion to VALID_TOOLS and /start command The /start command session got stuck because AskUserQuestion was not included in the allowed-tools whitelist. This fix addresses three issues: 1. VALID_TOOLS in spec-validator was missing AskUserQuestion, TodoWrite, Agent, and NotebookEdit — preventing commands from declaring these Claude Code built-in tools in their allowed-tools. 2. The /start command template now explicitly includes AskUserQuestion in its allowed-tools frontmatter and instructs the agent to use it for interactive guided choices (Phase 3). 3. Added /start command spec to commands.yaml with AskUserQuestion as a declared tool dependency. Also adds a test case validating all four newly-added tools are accepted by the spec validator. https://claude.ai/code/session_01Qh3Xk3jFkVdeRAXTqLvq3M * fix(commands): remove unrendered Handlebars comment from start.md output The generated .claude/commands/start.md contained a raw {{! ... }} Handlebars comment that was not processed by the sync engine. Remove it so the generated output is clean Markdown. https://claude.ai/code/session_01Qh3Xk3jFkVdeRAXTqLvq3M --------- Co-authored-by: Claude <noreply@anthropic.com> * Add configurable prefix to kits commands (#388) * feat(sync): add configurable command prefix for generated slash commands Add `commandPrefix` setting to overlay settings that namespaces all generated slash commands across platforms: - Claude Code: subdirectory strategy (kits/check.md → /project:kits:check) - Cursor/Windsurf/Copilot/Codex: filename prefix (kits-check.md → /kits-check) - Team commands excluded from prefixing (already namespaced) Changes: - Add resolveCommandPath() helper with subdirectory/filename strategies - Update syncClaudeCommands, syncClaudeSkills, syncCursorCommands, syncWindsurfCommands, syncCopilotPrompts, syncCodexSkills - Add commandPrefix to vars from overlay settings - Add commandPrefixedName to buildCommandVars - Add 16 unit + integration tests (all pass, 93 existing tests unaffected) Default is null (no prefix) for full backwards compatibility. https://claude.ai/code/session_01EBjmVEhi7fP2huAL3SBR6p * fix(sync): address review findings for command prefix - Remove unused afterAll import from test file - Add clarifying comment that non-spec command files are also prefixed - Add 2 integration tests verifying commandPrefixedName template variable renders correctly with and without prefix https://claude.ai/code/session_01EBjmVEhi7fP2huAL3SBR6p --------- Co-authored-by: Claude <noreply@anthropic.com> * fix(ci): CI remediation — package manager, review findings, test stability (#390) * fix(ci): resolve 7 bugs from project review - BUG-001: Replace flaky discover test with controlled temp fixture - BUG-002: Run prettier --write to fix formatting drift - BUG-003: Add form-template detection skip in issue label validation - BUG-005: Change claude.yml to self-hosted runner - BUG-006: Align branch protection required status checks with project.yaml - BUG-007: Fix command injection in resolve-merge.sh (use grep -F) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * docs: update changelog, add planning registry review findings - Add changelog entries for Wave 1-3 fixes (Added/Changed/Fixed/Removed) - Add Project Review Findings section to planning registry (PR-001 to PR-014) - Update planning docs after sync merge Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(review): add --generate-plans flag to project-review command Add Phase 2.5 plan generation after project review findings. When --generate-plans is passed (default: true), scaffold plan files from critical/high findings into docs/planning/review-findings/. Also includes sync cleanup of stale cursor/windsurf settings. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore(sync): regenerate all outputs after project review fixes Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(cli): dynamic flag loading from commands.yaml + context-aware template hook - Replace ~200 lines of hardcoded VALID_FLAGS/FLAG_TYPES with loadCommandFlags() that reads flag definitions from commands.yaml at startup - CLI_INTERNAL_FLAGS/CLI_INTERNAL_FLAG_TYPES cover commands not in commands.yaml - Self-validation warns at startup if any flag is missing a type definition - Update cli.test.mjs to validate CLI_INTERNAL_FLAGS consistency - Fix scaffold-once orphan bug: carry forward manifest entries for files skipped by scaffold-once so orphan cleanup does not delete them - Make protect-templates hook context-aware: skip protection in the agentkit-forge source repo (detected via package.json name) so maintainer agents can edit templates; block only in downstream repos Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(sync): add managed-mode script templates for downstream repos Add 14 script templates (.agentkit/templates/scripts/) with `managed` scaffold mode so downstream repos receive script updates via three-way merge while preserving local customizations. Templates include: create-doc, update-changelog, validate-documentation, validate-numbering, check-documentation-requirement, sync-issues, sync-split-pr, setup-agentkit-branch-governance, and resolve-merge (both .sh and .ps1 variants where applicable). Parameterized templates use {{defaultBranch}} and branch protection variables from project.yaml. Engine wired via syncScripts() under doc-scaffolding feature gate. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(teams): add TeamForge meta-team for agent team creation (cogmesh #130) Add the TEAMFORGE meta-team (T11) — a structured pipeline for creating, validating, and deploying new agent team specifications. Adapted from cogmesh #130 with a simplified 6-agent pipeline: - input-clarifier: assess requests, extract constraints - mission-definer: lock team definition (ID, scope, accepts) - role-architect: design agent roles and dependencies - prompt-engineer: write agent descriptions and rules - flow-designer: design team command and integration points - team-validator: quality gate for spec consistency Includes /team-forge command with --task flag (create-team, validate-team, audit-teams, update-team) and planning doc. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(teams): add Strategic Ops team for cross-project coordination Add the STRATEGIC OPS team (T12) — handles framework governance, portfolio analysis, adoption strategy, impact assessment, and release coordination across all repos using AgentKit Forge. 5-agent pipeline: - portfolio-analyst: inventory repos, detect drift, adoption metrics - governance-advisor: versioning strategy, breaking change protocols - adoption-strategist: onboarding, migration paths, rollout plans - impact-assessor: blast radius analysis for template/spec changes - release-coordinator: version bumps, sync waves, release comms Includes /team-strategic-ops command with --task and --scope flags. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(agents): add agent/team relationship matrix analysis engine + scripts Add comprehensive agent/team relationship analysis with 8 cross-reference matrices and 10 supplementary analyses (orphans, cycles, bottlenecks, reachability, critical path, notification amplifiers, etc.). - Fix YAML structure: strategic-ops agents now under own top-level key - Add explicit agents: lists to forge + strategic-ops teams in teams.yaml - Add consolidation detection responsibilities to portfolio-analyst - Create agent-analysis.mjs engine module (loadFullAgentGraph + renderers) - Wire analyze-agents CLI command with --output/--matrix/--format flags - Add managed-scaffold script templates (bash + PowerShell) - Integrate into sync pipeline (auto-regenerates matrix on spec changes) - Add 33 tests covering all matrices, analyses, and edge cases Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: update documentation files and add plan template - Add trailing newlines to Cursor command documentation files for consistency - Add new plan template files for project planning - Improve markdown table formatting in Claude skills documentation - Remove obsolete .clinerules/testing.md file - Update various rule files with better formatting and advisory rule alignment * feat(agents): add spec-compliance-auditor feedback loop + Cost Ops team (T14) - Add spec-compliance-auditor to operations category (quality team) — closes the feedback loop between agent specs and actual behavior - Add Cost Ops team (T14) with 5 agents: model-economist, token-efficiency-engineer, vendor-arbitrage-analyst, grant-hunter, cost-ops-monitor - Add ai-cost-ops rules domain with 6 conventions (model routing, token budgets, caching, batch APIs, vendor abstraction, credit tracking) - Add team-cost-ops command with --task, --period, --provider flags - Update notification chains: data→cost-ops-monitor, infra→model-economist, retrospective-analyst→spec-compliance-auditor - Add intake routes: cost-ops, agent-performance Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(teams): add implement to cost-ops team accepts list Resolves agent/team accepts mismatch — token-efficiency-engineer accepts implement but the team definition only had investigate/review/plan/document. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(cost-ops): add multi-provider infra cost ticket to backlog Add detailed planning ticket for multi-provider infrastructure cost normalisation, routing, and cost-agent integration. Covers 9 providers (Anthropic, OpenAI, Google, Mistral, Cohere, self-hosted, Azure, AWS, GCP) with 3-phase delivery plan and cross-team dependency tracking. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(templates): resolve PR review comments from CodeRabbit - Fix protect-templates.sh: package name check uses correct "agentkit-forge-runtime" instead of "agentkit-forge" - Fix protect-templates.ps1: malformed path (missing separator before .agentkit) and same package name correction - Fix update-changelog.ps1: change .mjs to .cjs to match CommonJS require() syntax used in the inline Node script - Fix resolve-merge.sh: add fallback for {{defaultBranch}} placeholder - Fix AGENT_TEAMS.md: resolve three-way merge conflict markers left by sync engine, keeping user formatting + implement in cost-ops Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(cost-ops): add WebSearch/WebFetch tools to cost-ops agents Enable web research capabilities for cost-ops team: - Add WebSearch and WebFetch to /team-cost-ops allowed-tools - Add WebSearch and WebFetch to model-economist, vendor-arbitrage-analyst, and grant-hunter agent preferred-tools - Add web intake expansion ticket (P2) for MCP crawler, Puppeteer integration, automated pricing refresh, and cross-session persistence - Regenerate sync outputs Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(cost-ops): add Cost Ops team, agents, and multi-provider cost ticket (#364) * feat(agents): add spec-compliance-auditor feedback loop + Cost Ops team (T14) - Add spec-compliance-auditor to operations category (quality team) — closes the feedback loop between agent specs and actual behavior - Add Cost Ops team (T14) with 5 agents: model-economist, token-efficiency-engineer, vendor-arbitrage-analyst, grant-hunter, cost-ops-monitor - Add ai-cost-ops rules domain with 6 conventions (model routing, token budgets, caching, batch APIs, vendor abstraction, credit tracking) - Add team-cost-ops command with --task, --period, --provider flags - Update notification chains: data→cost-ops-monitor, infra→model-economist, retrospective-analyst→spec-compliance-auditor - Add intake routes: cost-ops, agent-performance Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(teams): add implement to cost-ops team accepts list Resolves agent/team accepts mismatch — token-efficiency-engineer accepts implement but the team definition only had investigate/review/plan/document. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(cost-ops): add multi-provider infra cost ticket to backlog Add detailed planning ticket for multi-provider infrastructure cost normalisation, routing, and cost-agent integration. Covers 9 providers (Anthropic, OpenAI, Google, Mistral, Cohere, self-hosted, Azure, AWS, GCP) with 3-phase delivery plan and cross-team dependency tracking. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(templates): resolve PR review comments from CodeRabbit - Fix protect-templates.sh: package name check uses correct "agentkit-forge-runtime" instead of "agentkit-forge" - Fix protect-templates.ps1: malformed path (missing separator before .agentkit) and same package name correction - Fix update-changelog.ps1: change .mjs to .cjs to match CommonJS require() syntax used in the inline Node script - Fix resolve-merge.sh: add fallback for {{defaultBranch}} placeholder - Fix AGENT_TEAMS.md: resolve three-way merge conflict markers left by sync engine, keeping user formatting + implement in cost-ops Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(cost-ops): add WebSearch/WebFetch tools to cost-ops agents (#365) Enable web research capabilities for cost-ops team: - Add WebSearch and WebFetch to /team-cost-ops allowed-tools - Add WebSearch and WebFetch to model-economist, vendor-arbitrage-analyst, and grant-hunter agent preferred-tools - Add web intake expansion ticket (P2) for MCP crawler, Puppeteer integration, automated pricing refresh, and cross-session persistence - Regenerate sync outputs Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> * fix(teams): address CodeRabbit review findings on strategic-ops PR - Lazy-load js-yaml in cli.mjs after ensureDependencies() to prevent crash when node_modules is missing - Convert YAML frontmatter to PowerShell comment blocks in all 6 PS1 templates to fix invalid PowerShell syntax - Fix protect-templates hook path: use 3 parent traversals to reach .agentkit/package.json from hooks directory - Remove schema-invalid 'phase' field from ai-cost-ops rule domain - Narrow strategic-ops scope: replace **/* catch-all with specific files - Add strategic-ops to cost-ops handoff-chain for consistency - Add Write tool to spec-compliance-auditor, vendor-arbitrage-analyst, and grant-hunter agents - Fix glob matching in resolve-merge.sh (use regex instead of broken sed strip) - Add merge failure vs conflict detection in resolve-merge.ps1 - Add branch existence check in setup-agentkit-branch-governance scripts - Add gh CLI preflight check in sync-split-pr.ps1 - Deduplicate branch protection loop when defaultBranch is 'main' - Fix applies-to glob: docs/planning/cost/** → docs/planning/cost-governance/** - Fix non-canonical doc paths in intake-agent-proposal.md - Add changelog entries for new teams, agents, and analysis engine - Resolve AGENT_TEAMS.md merge conflict (accept narrowed scope) - Run prettier on all modified files Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(templates): add gh auth preflight and changelog divider handling - sync-split-pr.ps1: add gh auth status check before side effects - update-changelog.ps1: stop before --- divider when appending entries Addresses CodeRabbit review comments #7 and #13 on PR #356. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(sync): set executable permission on analyze-agents.sh Linux CI sync produces +x permissions; align local to match. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(templates): address CodeRabbit review round 3-4 findings - Fix YAML frontmatter in copilot agent template: use double quotes for description field to handle apostrophes (CRITICAL) - Fix protect-templates.sh/ps1 path traversal: correct parent directory count for .agentkit/package.json source repo detection - Add $PSNativeCommandUseErrorActionPreference to sync-split-pr.ps1 so native command failures (git, pnpm, gh) are treated as fatal - Replace try/catch with $LASTEXITCODE check for gh auth status - Deduplicate branch loop in setup-agentkit-branch-governance.sh when defaultBranch equals 'main' - Fix duplicate verification echo lines in governance scripts Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * style(docs): fix prettier formatting on planning documents Run prettier --write on web-intake-expansion.md and intake-agent-proposal.md to fix CI formatting check. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(tests): isolate render target gating tests with fresh temp dirs Tests in the "render target gating" describe block shared a single temp directory via beforeAll/afterAll. The first test ran --only claude (generating .claude/ files), and the second ran --only warp expecting no Claude files — but leftovers from test 1 caused the assertion to fail. Changing to beforeEach/afterEach gives each test a clean directory. Closes #377 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(commands): add /start command as new user entry point Adds a context-aware triage command that detects repository state (fresh clone, post-discovery, mid-session, uncommitted work) and guides users to the right command or team for their goal. Includes team routing table, 4 contextual flows, and decision guidance for when users don't know which team to use. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * refactor(commands): add Arguments and State Management sections to /start Addresses TEAMFORGE validation findings: - Add dedicated Arguments section documenting $ARGUMENTS handling - Add State Management section (reads/writes inventory) - Fix frontmatter: remove misleading generated_by field - Add explicit "manually authored" comment header https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): add /start to spec and template for cross-repo generation Moves /start from a hand-authored command to a proper spec-driven, sync-generated command available to any repo that adopts AgentKit Forge. - Add start command definition to commands.yaml (no feature gate — always on) - Create start.md template in .agentkit/templates/claude/commands/ - Add /start to CLAUDE.md Quick Reference table template https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after adding /start command Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): make /start team routing dynamic instead of hardcoded Replace the static team routing table with dynamic discovery: 1. Read AGENT_TEAMS.md (from /discover) at runtime 2. Fall back to .agentkit/spec/teams.yaml 3. Fall back to /team-* command frontmatter This ensures /start always reflects the actual teams configured in any repo, rather than a hardcoded list that could go stale. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after dynamic routing change Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add interactive TUI entry point with hybrid UI Replace static markdown output with an ink-based terminal UI that combines two modes: a guided conversation flow for first-run users and a fuzzy-searchable command palette for returning users. A persistent status bar shows repo state at a glance (branch, phase, backlog count, working tree status). - Context detection module mirrors /start Phase 1 signals - ConversationFlow: branching dialogue tree (choose-your-own-adventure) - CommandPalette: fuzzy search with context-ranked star recommendations - StatusBar: tmux-style persistent strip with color-coded segments - Supports --json flag for scripting/piping https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add test suite, error handling, and refactor for production readiness - Add vitest test infrastructure with 102 tests across 7 files - Coverage: 95.58% statements, 90.81% branches, 96.72% functions - Extract conversation tree to separate config module for testability - Add error boundary to App component for graceful error display - Add --help flag with usage documentation - Add TTY detection with JSON fallback for non-interactive environments - Add SIGINT/SIGTERM signal handling for clean exit https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore: add coverage to gitignore, include plan and workspace config https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — unused code, git cwd, magic numbers - Call exit() after command selection so Ink process terminates - Remove unused ctx prop from Header component - Fix git commands to use -C flag with root path parameter - Extract dumpContextJson() helper to deduplicate JSON output logic - Add comment explaining hardcoded team filter exclusion - Replace magic numbers with named constants (FUSE_THRESHOLD, RECOMMENDED_SCORE, MAX_BRANCH_LENGTH) - Remove unused ink-spinner dependency - Add test verifying git -C flag passes root correctly https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — security, correctness, test quality - CRITICAL: Replace execSync shell interpolation with execFileSync to prevent command injection via root parameter in detect.js - CRITICAL: Remove phantom --external:ink-spinner from build script and switch npx to direct esbuild invocation - HIGH: Fix exit race condition — use useEffect instead of setTimeout - HIGH: Wire up onSelect callback in ConversationFlow so Guide mode triggers the result screen in App - HIGH: Destructure and accept ctx prop in ConversationFlow - HIGH: Add back-navigation (Escape) in ConversationFlow - HIGH: Guard against undefined team.focus in commands.js tags - MEDIUM: Use functional setCursor form to avoid stale closures - MEDIUM: Key commandIndices Map by string id instead of object identity - MEDIUM: Improve parseTeams header detection (drop first row approach) - MEDIUM: Filter completed/done/closed items from backlogCount - MEDIUM: Extract shared makeCtx test utility across all test files - MEDIUM: Add null guard to StatusBar truncate helper - LOW: Validate orchestratorPhase is a number in range 1-5 - LOW: Fix pnpm-workspace.yaml list syntax - Replace all setTimeout in tests with vi.waitFor deterministic waits https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(engine): add pre-sync commit guard and interactive apply mode Adds two safety features to the sync pipeline: 1. Pre-sync commit guard: Detects uncommitted changes in protected directories (.agentkit/engines, spec, overlays) before sync runs. In TTY mode, prompts to abort, stash, or continue. In non-TTY mode (CI), prints a warning and proceeds. 2. Interactive apply mode: After rendering, shows a change summary and prompts: apply all / skip all / prompt each file. Per-file prompt supports show-diff and apply-all-remaining. Default in TTY; bypassed with --yes, --no-prompt, or --force. New module: sync-guard.mjs with 4 exported functions and 7 tests. New CLI flags: --yes, --no-prompt for non-interactive sync. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore(sync): regenerate outputs after branch merges Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore(sync): regenerate outputs after merge of new-user-entry-point Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(engine): add configurable package manager and fix review findings - Add `stack.packageManager` field to project.yaml (pnpm | npm | yarn) - Derive helper template vars (pmInstall, pmRun, pmExec, pmLockfile, etc.) - Update CLAUDE.md template and hook/workflow templates to use {{packageManager}} - Fix sync-guard to exclude .agentkit/spec from protected dirs and add try/catch - Remove duplicate cost-ops team definition from teams.yaml - Pin all dependency versions in package.json (remove ^ prefixes) - Add vitest coverage thresholds (80% statements/branches/functions/lines) - Fix src/start/ code quality: null guards, exit delay, error boundaries - Harden consolidate-branches.sh: self-resolution guard, stash restore - Regenerate all 533 output files via agentkit sync Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore(engine): add brand color palette variables to sync vars Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(ci): fix test race condition, workspace config, and lockfile - Fix ConversationFlow test: wait for 'Got it' before asserting hint text - Add packages field to pnpm-workspace.yaml for proper workspace resolution - Regenerate lockfile after version pinning (removed ^ prefixes) - Remove accidental .agentkit/templates/src/ artifacts Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(start): add event loop yields to ConversationFlow tests ink-select-input needs setImmediate yields after a new menu renders before it can process ENTER keypresses. Without this, the second ENTER in leaf-selection tests was swallowed, causing intermittent failures. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> * fix(spec): correct githubSlug to phoenixvc/agentkit-forge (#391) Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> * Add entry point for new framework users (#389) * feat(commands): add /start command as new user entry point Adds a context-aware triage command that detects repository state (fresh clone, post-discovery, mid-session, uncommitted work) and guides users to the right command or team for their goal. Includes team routing table, 4 contextual flows, and decision guidance for when users don't know which team to use. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * refactor(commands): add Arguments and State Management sections to /start Addresses TEAMFORGE validation findings: - Add dedicated Arguments section documenting $ARGUMENTS handling - Add State Management section (reads/writes inventory) - Fix frontmatter: remove misleading generated_by field - Add explicit "manually authored" comment header https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): add /start to spec and template for cross-repo generation Moves /start from a hand-authored command to a proper spec-driven, sync-generated command available to any repo that adopts AgentKit Forge. - Add start command definition to commands.yaml (no feature gate — always on) - Create start.md template in .agentkit/templates/claude/commands/ - Add /start to CLAUDE.md Quick Reference table template https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after adding /start command Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): make /start team routing dynamic instead of hardcoded Replace the static team routing table with dynamic discovery: 1. Read AGENT_TEAMS.md (from /discover) at runtime 2. Fall back to .agentkit/spec/teams.yaml 3. Fall back to /team-* command frontmatter This ensures /start always reflects the actual teams configured in any repo, rather than a hardcoded list that could go stale. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after dynamic routing change Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add interactive TUI entry point with hybrid UI Replace static markdown output with an ink-based terminal UI that combines two modes: a guided conversation flow for first-run users and a fuzzy-searchable command palette for returning users. A persistent status bar shows repo state at a glance (branch, phase, backlog count, working tree status). - Context detection module mirrors /start Phase 1 signals - ConversationFlow: branching dialogue tree (choose-your-own-adventure) - CommandPalette: fuzzy search with context-ranked star recommendations - StatusBar: tmux-style persistent strip with color-coded segments - Supports --json flag for scripting/piping https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add test suite, error handling, and refactor for production readiness - Add vitest test infrastructure with 102 tests across 7 files - Coverage: 95.58% statements, 90.81% branches, 96.72% functions - Extract conversation tree to separate config module for testability - Add error boundary to App component for graceful error display - Add --help flag with usage documentation - Add TTY detection with JSON fallback for non-interactive environments - Add SIGINT/SIGTERM signal handling for clean exit https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore: add coverage to gitignore, include plan and workspace config https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — unused code, git cwd, magic numbers - Call exit() after command selection so Ink process terminates - Remove unused ctx prop from Header component - Fix git commands to use -C flag with root path parameter - Extract dumpContextJson() helper to deduplicate JSON output logic - Add comment explaining hardcoded team filter exclusion - Replace magic numbers with named constants (FUSE_THRESHOLD, RECOMMENDED_SCORE, MAX_BRANCH_LENGTH) - Remove unused ink-spinner dependency - Add test verifying git -C flag passes root correctly https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — security, correctness, test quality - CRITICAL: Replace execSync shell interpolation with execFileSync to prevent command injection via root parameter in detect.js - CRITICAL: Remove phantom --external:ink-spinner from build script and switch npx to direct esbuild invocation - HIGH: Fix exit race condition — use useEffect instead of setTimeout - HIGH: Wire up onSelect callback in ConversationFlow so Guide mode triggers the result screen in App - HIGH: Destructure and accept ctx prop in ConversationFlow - HIGH: Add back-navigation (Escape) in ConversationFlow - HIGH: Guard against undefined team.focus in commands.js tags - MEDIUM: Use functional setCursor form to avoid stale closures - MEDIUM: Key commandIndices Map by string id instead of object identity - MEDIUM: Improve parseTeams header detection (drop first row approach) - MEDIUM: Filter completed/done/closed items from backlogCount - MEDIUM: Extract shared makeCtx test utility across all test files - MEDIUM: Add null guard to StatusBar truncate helper - LOW: Validate orchestratorPhase is a number in range 1-5 - LOW: Fix pnpm-workspace.yaml list syntax - Replace all setTimeout in tests with vi.waitFor deterministic waits https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * test(start): add coverage for result screen exit path Add App-level test that navigates through ConversationFlow to a leaf node and verifies the result screen text is rendered before exit(). Confirms the synchronous useEffect exit is safe — React commits the render (Ink captures the frame) before useEffect fires. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore: update generated sync output timestamps Generated files updated with current sync date from dev merge. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW --------- Co-authored-by: Claude <noreply@anthropic.com> * fix: caldues heuristics (#398) * feat: complete revisit of agents (#399) (#400) * Add start command: new user entry point with state detection (#387) * fix(commands): add AskUserQuestion to VALID_TOOLS and /start command The /start command session got stuck because AskUserQuestion was not included in the allowed-tools whitelist. This fix addresses three issues: 1. VALID_TOOLS in spec-validator was missing AskUserQuestion, TodoWrite, Agent, and NotebookEdit — preventing commands from declaring these Claude Code built-in tools in their allowed-tools. 2. The /start command template now explicitly includes AskUserQuestion in its allowed-tools frontmatter and instructs the agent to use it for interactive guided choices (Phase 3). 3. Added /start command spec to commands.yaml with AskUserQuestion as a declared tool dependency. Also adds a test case validating all four newly-added tools are accepted by the spec validator. https://claude.ai/code/session_01Qh3Xk3jFkVdeRAXTqLvq3M * fix(commands): remove unrendered Handlebars comment from start.md output The generated .claude/commands/start.md contained a raw {{! ... }} Handlebars comment that was not processed by the sync engine. Remove it so the generated output is clean Markdown. https://claude.ai/code/session_01Qh3Xk3jFkVdeRAXTqLvq3M --------- * Add configurable prefix to kits commands (#388) * feat(sync): add configurable command prefix for generated slash commands Add `commandPrefix` setting to overlay settings that namespaces all generated slash commands across platforms: - Claude Code: subdirectory strategy (kits/check.md → /project:kits:check) - Cursor/Windsurf/Copilot/Codex: filename prefix (kits-check.md → /kits-check) - Team commands excluded from prefixing (already namespaced) Changes: - Add resolveCommandPath() helper with subdirectory/filename strategies - Update syncClaudeCommands, syncClaudeSkills, syncCursorCommands, syncWindsurfCommands, syncCopilotPrompts, syncCodexSkills - Add commandPrefix to vars from overlay settings - Add commandPrefixedName to buildCommandVars - Add 16 unit + integration tests (all pass, 93 existing tests unaffected) Default is null (no prefix) for full backwards compatibility. https://claude.ai/code/session_01EBjmVEhi7fP2huAL3SBR6p * fix(sync): address review findings for command prefix - Remove unused afterAll import from test file - Add clarifying comment that non-spec command files are also prefixed - Add 2 integration tests verifying commandPrefixedName template variable renders correctly with and without prefix https://claude.ai/code/session_01EBjmVEhi7fP2huAL3SBR6p --------- * fix(ci): CI remediation — package manager, review findings, test stability (#390) * fix(ci): resolve 7 bugs from project review - BUG-001: Replace flaky discover test with controlled temp fixture - BUG-002: Run prettier --write to fix formatting drift - BUG-003: Add form-template detection skip in issue label validation - BUG-005: Change claude.yml to self-hosted runner - BUG-006: Align branch protection required status checks with project.yaml - BUG-007: Fix command injection in resolve-merge.sh (use grep -F) * docs: update changelog, add planning registry review findings - Add changelog entries for Wave 1-3 fixes (Added/Changed/Fixed/Removed) - Add Project Review Findings section to planning registry (PR-001 to PR-014) - Update planning docs after sync merge * feat(review): add --generate-plans flag to project-review command Add Phase 2.5 plan generation after project review findings. When --generate-plans is passed (default: true), scaffold plan files from critical/high findings into docs/planning/review-findings/. Also includes sync cleanup of stale cursor/windsurf settings. * chore(sync): regenerate all outputs after project review fixes * feat(cli): dynamic flag loading from commands.yaml + context-aware template hook - Replace ~200 lines of hardcoded VALID_FLAGS/FLAG_TYPES with loadCommandFlags() that reads flag definitions from commands.yaml at startup - CLI_INTERNAL_FLAGS/CLI_INTERNAL_FLAG_TYPES cover commands not in commands.yaml - Self-validation warns at startup if any flag is missing a type definition - Update cli.test.mjs to validate CLI_INTERNAL_FLAGS consistency - Fix scaffold-once orphan bug: carry forward manifest entries for files skipped by scaffold-once so orphan cleanup does not delete them - Make protect-templates hook context-aware: skip protection in the agentkit-forge source repo (detected via package.json name) so maintainer agents can edit templates; block only in downstream repos * feat(sync): add managed-mode script templates for downstream repos Add 14 script templates (.agentkit/templates/scripts/) with `managed` scaffold mode so downstream repos receive script updates via three-way merge while preserving local customizations. Templates include: create-doc, update-changelog, validate-documentation, validate-numbering, check-documentation-requirement, sync-issues, sync-split-pr, setup-agentkit-branch-governance, and resolve-merge (both .sh and .ps1 variants where applicable). Parameterized templates use {{defaultBranch}} and branch protection variables from project.yaml. Engine wired via syncScripts() under doc-scaffolding feature gate. * feat(teams): add TeamForge meta-team for agent team creation (cogmesh #130) Add the TEAMFORGE meta-team (T11) — a structured pipeline for creating, validating, and deploying new agent team specifications. Adapted from cogmesh #130 with a simplified 6-agent pipeline: - input-clarifier: assess requests, extract constraints - mission-definer: lock team definition (ID, scope, accepts) - role-architect: design agent roles and dependencies - prompt-engineer: write agent descriptions and rules - flow-designer: design team command and integration points - team-validator: quality gate for spec consistency Includes /team-forge command with --task flag (create-team, validate-team, audit-teams, update-team) and planning doc. * feat(teams): add Strategic Ops team for cross-project coordination Add the STRATEGIC OPS team (T12) — handles framework governance, portfolio analysis, adoption strategy, impact assessment, and release coordination across all repos using AgentKit Forge. 5-agent pipeline: - portfolio-analyst: inventory repos, detect drift, adoption metrics - governance-advisor: versioning strategy, breaking change protocols - adoption-strategist: onboarding, migration paths, rollout plans - impact-assessor: blast radius analysis for template/spec changes - release-coordinator: version bumps, sync waves, release comms Includes /team-strategic-ops command with --task and --scope flags. * feat(agents): add agent/team relationship matrix analysis engine + scripts Add comprehensive agent/team relationship analysis with 8 cross-reference matrices and 10 supplementary analyses (orphans, cycles, bottlenecks, reachability, critical path, notification amplifiers, etc.). - Fix YAML structure: strategic-ops agents now under own top-level key - Add explicit agents: lists to forge + strategic-ops teams in teams.yaml - Add consolidation detection responsibilities to portfolio-analyst - Create agent-analysis.mjs engine module (loadFullAgentGraph + renderers) - Wire analyze-agents CLI command with --output/--matrix/--format flags - Add managed-scaffold script templates (bash + PowerShell) - Integrate into sync pipeline (auto-regenerates matrix on spec changes) - Add 33 tests covering all matrices, analyses, and edge cases * chore: update documentation files and add plan template - Add trailing newlines to Cursor command documentation files for consistency - Add new plan template files for project planning - Improve markdown table formatting in Claude skills documentation - Remove obsolete .clinerules/testing.md file - Update various rule files with better formatting and advisory rule alignment * feat(agents): add spec-compliance-auditor feedback loop + Cost Ops team (T14) - Add spec-compliance-auditor to operations category (quality team) — closes the feedback loop between agent specs and actual behavior - Add Cost Ops team (T14) with 5 agents: model-economist, token-efficiency-engineer, vendor-arbitrage-analyst, grant-hunter, cost-ops-monitor - Add ai-cost-ops rules domain with 6 conventions (model routing, token budgets, caching, batch APIs, vendor abstraction, credit tracking) - Add team-cost-ops command with --task, --period, --provider flags - Update notification chains: data→cost-ops-monitor, infra→model-economist, retrospective-analyst→spec-compliance-auditor - Add intake routes: cost-ops, agent-performance * fix(teams): add implement to cost-ops team accepts list Resolves agent/team accepts mismatch — token-efficiency-engineer accepts implement but the team definition only had investigate/review/plan/document. * feat(cost-ops): add multi-provider infra cost ticket to backlog Add detailed planning ticket for multi-provider infrastructure cost normalisation, routing, and cost-agent integration. Covers 9 providers (Anthropic, OpenAI, Google, Mistral, Cohere, self-hosted, Azure, AWS, GCP) with 3-phase delivery plan and cross-team dependency tracking. * fix(templates): resolve PR review comments from CodeRabbit - Fix protect-templates.sh: package name check uses correct "agentkit-forge-runtime" instead of "agentkit-forge" - Fix protect-templates.ps1: malformed path (missing separator before .agentkit) and same package name correction - Fix update-changelog.ps1: change .mjs to .cjs to match CommonJS require() syntax used in the inline Node script - Fix resolve-merge.sh: add fallback for {{defaultBranch}} placeholder - Fix AGENT_TEAMS.md: resolve three-way merge conflict markers left by sync engine, keeping user formatting + implement in cost-ops * feat(cost-ops): add WebSearch/WebFetch tools to cost-ops agents Enable web research capabilities for cost-ops team: - Add WebSearch and WebFetch to /team-cost-ops allowed-tools - Add WebSearch and WebFetch to model-economist, vendor-arbitrage-analyst, and grant-hunter agent preferred-tools - Add web intake expansion ticket (P2) for MCP crawler, Puppeteer integration, automated pricing refresh, and cross-session persistence - Regenerate sync outputs * feat(cost-ops): add Cost Ops team, agents, and multi-provider cost ticket (#364) * feat(agents): add spec-compliance-auditor feedback loop + Cost Ops team (T14) - Add spec-compliance-auditor to operations category (quality team) — closes the feedback loop between agent specs and actual behavior - Add Cost Ops team (T14) with 5 agents: model-economist, token-efficiency-engineer, vendor-arbitrage-analyst, grant-hunter, cost-ops-monitor - Add ai-cost-ops rules domain with 6 conventions (model routing, token budgets, caching, batch APIs, vendor abstraction, credit tracking) - Add team-cost-ops command with --task, --period, --provider flags - Update notification chains: data→cost-ops-monitor, infra→model-economist, retrospective-analyst→spec-compliance-auditor - Add intake routes: cost-ops, agent-performance * fix(teams): add implement to cost-ops team accepts list Resolves agent/team accepts mismatch — token-efficiency-engineer accepts implement but the team definition only had investigate/review/plan/document. * feat(cost-ops): add multi-provider infra cost ticket to backlog Add detailed planning ticket for multi-provider infrastructure cost normalisation, routing, and cost-agent integration. Covers 9 providers (Anthropic, OpenAI, Google, Mistral, Cohere, self-hosted, Azure, AWS, GCP) with 3-phase delivery plan and cross-team dependency tracking. * fix(templates): resolve PR review comments from CodeRabbit - Fix protect-templates.sh: package name check uses correct "agentkit-forge-runtime" instead of "agentkit-forge" - Fix protect-templates.ps1: malformed path (missing separator before .agentkit) and same package name correction - Fix update-changelog.ps1: change .mjs to .cjs to match CommonJS require() syntax used in the inline Node script - Fix resolve-merge.sh: add fallback for {{defaultBranch}} placeholder - Fix AGENT_TEAMS.md: resolve three-way merge conflict markers left by sync engine, keeping user formatting + implement in cost-ops * feat(cost-ops): add WebSearch/WebFetch tools to cost-ops agents (#365) Enable web research capabilities for cost-ops team: - Add WebSearch and WebFetch to /team-cost-ops allowed-tools - Add WebSearch and WebFetch to model-economist, vendor-arbitrage-analyst, and grant-hunter agent preferred-tools - Add web intake expansion ticket (P2) for MCP crawler, Puppeteer integration, automated pricing refresh, and cross-session persistence - Regenerate sync outputs --------- * fix(teams): address CodeRabbit review findings on strategic-ops PR - Lazy-load js-yaml in cli.mjs after ensureDependencies() to prevent crash when node_modules is missing - Convert YAML frontmatter to PowerShell comment blocks in all 6 PS1 templates to fix invalid PowerShell syntax - Fix protect-templates hook path: use 3 parent traversals to reach .agentkit/package.json from hooks directory - Remove schema-invalid 'phase' field from ai-cost-ops rule domain - Narrow strategic-ops scope: replace **/* catch-all with specific files - Add strategic-ops to cost-ops handoff-chain for consistency - Add Write tool to spec-compliance-auditor, vendor-arbitrage-analyst, and grant-hunter agents - Fix glob matching in resolve-merge.sh (use regex instead of broken sed strip) - Add merge failure vs conflict detection in resolve-merge.ps1 - Add branch existence check in setup-agentkit-branch-governance scripts - Add gh CLI preflight check in sync-split-pr.ps1 - Deduplicate branch protection loop when defaultBranch is 'main' - Fix applies-to glob: docs/planning/cost/** → docs/planning/cost-governance/** - Fix non-canonical doc paths in intake-agent-proposal.md - Add changelog entries for new teams, agents, and analysis engine - Resolve AGENT_TEAMS.md merge conflict (accept narrowed scope) - Run prettier on all modified files * fix(templates): add gh auth preflight and changelog divider handling - sync-split-pr.ps1: add gh auth status check before side effects - update-changelog.ps1: stop before --- divider when appending entries Addresses CodeRabbit review comments #7 and #13 on PR #356. * fix(sync): set executable permission on analyze-agents.sh Linux CI sync produces +x permissions; align local to match. * fix(templates): address CodeRabbit review round 3-4 findings - Fix YAML frontmatter in copilot agent template: use double quotes for description field to handle apostrophes (CRITICAL) - Fix protect-templates.sh/ps1 path traversal: correct parent directory count for .agentkit/package.json source repo detection - Add $PSNativeCommandUseErrorActionPreference to sync-split-pr.ps1 so native command failures (git, pnpm, gh) are treated as fatal - Replace try/catch with $LASTEXITCODE check for gh auth status - Deduplicate branch loop in setup-agentkit-branch-governance.sh when defaultBranch equals 'main' - Fix duplicate verification echo lines in governance scripts * style(docs): fix prettier formatting on planning documents Run prettier --write on web-intake-expansion.md and intake-agent-proposal.md to fix CI formatting check. * fix(tests): isolate render target gating tests with fresh temp dirs Tests in the "render target gating" describe block shared a single temp directory via beforeAll/afterAll. The first test ran --only claude (generating .claude/ files), and the second ran --only warp expecting no Claude files — but leftovers from test 1 caused the assertion to fail. Changing to beforeEach/afterEach gives each test a clean directory. Closes #377 * feat(commands): add /start command as new user entry point Adds a context-aware triage command that detects repository state (fresh clone, post-discovery, mid-session, uncommitted work) and guides users to the right command or team for their goal. Includes team routing table, 4 contextual flows, and decision guidance for when users don't know which team to use. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * refactor(commands): add Arguments and State Management sections to /start Addresses TEAMFORGE validation findings: - Add dedicated Arguments section documenting $ARGUMENTS handling - Add State Management section (reads/writes inventory) - Fix frontmatter: remove misleading generated_by field - Add explicit "manually authored" comment header https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): add /start to spec and template for cross-repo generation Moves /start from a hand-authored command to a proper spec-driven, sync-generated command available to any repo that adopts AgentKit Forge. - Add start command definition to commands.yaml (no feature gate — always on) - Create start.md template in .agentkit/templates/claude/commands/ - Add /start to CLAUDE.md Quick Reference table template https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after adding /start command Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): make /start team routing dynamic instead of hardcoded Replace the static team routing table with dynamic discovery: 1. Read AGENT_TEAMS.md (from /discover) at runtime 2. Fall back to .agentkit/spec/teams.yaml 3. Fall back to /team-* command frontmatter This ensures /start always reflects the actual teams configured in any repo, rather than a hardcoded list that could go stale. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after dynamic routing change Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add interactive TUI entry point with hybrid UI Replace static markdown output with an ink-based terminal UI that combines two modes: a guided conversation flow for first-run users and a fuzzy-searchable command palette for returning users. A persistent status bar shows repo state at a glance (branch, phase, backlog count, working tree status). - Context detection module mirrors /start Phase 1 signals - ConversationFlow: branching dialogue tree (choose-your-own-adventure) - CommandPalette: fuzzy search with context-ranked star recommendations - StatusBar: tmux-style persistent strip with color-coded segments - Supports --json flag for scripting/piping https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add test suite, error handling, and refactor for production readiness - Add vitest test infrastructure with 102 tests across 7 files - Coverage: 95.58% statements, 90.81% branches, 96.72% functions - Extract conversation tree to separate config module for testability - Add error boundary to App component for graceful error display - Add --help flag with usage documentation - Add TTY detection with JSON fallback for non-interactive environments - Add SIGINT/SIGTERM signal handling for clean exit https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore: add coverage to gitignore, include plan and workspace config https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — unused code, git cwd, magic numbers - Call exit() after command selection so Ink process terminates - Remove unused ctx prop from Header component - Fix git commands to use -C flag with root path parameter - Extract dumpContextJson() helper to deduplicate JSON output logic - Add comment explaining hardcoded team filter exclusion - Replace magic numbers with named constants (FUSE_THRESHOLD, RECOMMENDED_SCORE, MAX_BRANCH_LENGTH) - Remove unused ink-spinner dependency - Add test verifying git -C flag passes root correctly https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — security, correctness, test quality - CRITICAL: Replace execSync shell interpolation with execFileSync to prevent command injection via root parameter in detect.js - CRITICAL: Remove phantom --external:ink-spinner from build script and switch npx to direct esbuild invocation - HIGH: Fix exit race condition — use useEffect instead of setTimeout - HIGH: Wire up onSelect callback in ConversationFlow so Guide mode triggers the result screen in App - HIGH: Destructure and accept ctx prop in ConversationFlow - HIGH: Add back-navigation (Escape) in ConversationFlow - HIGH: Guard against undefined team.focus in commands.js tags - MEDIUM: Use functional setCursor form to avoid stale closures - MEDIUM: Key commandIndices Map by string id instead of object identity - MEDIUM: Improve parseTeams header detection (drop first row approach) - MEDIUM: Filter completed/done/closed items from backlogCount - MEDIUM: Extract shared makeCtx test utility across all test files - MEDIUM: Add null guard to StatusBar truncate helper - LOW: Validate orchestratorPhase is a number in range 1-5 - LOW: Fix pnpm-workspace.yaml list syntax - Replace all setTimeout in tests with vi.waitFor deterministic waits https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(engine): add pre-sync commit guard and interactive apply mode Adds two safety features to the sync pipeline: 1. Pre-sync commit guard: Detects uncommitted changes in protected directories (.agentkit/engines, spec, overlays) before sync runs. In TTY mode, prompts to abort, stash, or continue. In non-TTY mode (CI), prints a warning and proceeds. 2. Interactive apply mode: After rendering, shows a change summary and prompts: apply all / skip all / prompt each file. Per-file prompt supports show-diff and apply-all-remaining. Default in TTY; bypassed with --yes, --no-prompt, or --force. New module: sync-guard.mjs with 4 exported functions and 7 tests. New CLI flags: --yes, --no-prompt for non-interactive sync. * chore(sync): regenerate outputs after branch merges * chore(sync): regenerate outputs after merge of new-user-entry-point * feat(engine): add configurable package manager and fix review findings - Add `stack.packageManager` field to project.yaml (pnpm | npm | yarn) - Derive helper template vars (pmInstall, pmRun, pmExec, pmLockfile, etc.) - Update CLAUDE.md template and hook/workflow templates to use {{packageManager}} - Fix sync-guard to exclude .agentkit/spec from protected dirs and add try/catch - Remove duplicate cost-ops team definition from teams.yaml - Pin all dependency versions in package.json (remove ^ prefixes) - Add vitest coverage thresholds (80% statements/branches/functions/lines) - Fix src/start/ code quality: null guards, exit delay, error boundaries - Harden consolidate-branches.sh: self-resolution guard, stash restore - Regenerate all 533 output files via agentkit sync * chore(engine): add brand color palette variables to sync vars * fix(ci): fix test race condition, workspace config, and lockfile - Fix ConversationFlow test: wait for 'Got it' before asserting hint text - Add packages field to pnpm-workspace.yaml for proper workspace resolution - Regenerate lockfile after version pinning (removed ^ prefixes) - Remove accidental .agentkit/templates/src/ artifacts * fix(start): add event loop yields to ConversationFlow tests ink-select-input needs setImmediate yields after a new menu renders before it can process ENTER keypresses. Without this, the second ENTER in leaf-selection tests was swallowed, causing intermittent failures. --------- * fix(spec): correct githubSlug to phoenixvc/agentkit-forge (#391) * Add entry point for new framework users (#389) * feat(commands): add /start command as new user entry point Adds a context-aware triage command that detects repository state (fresh clone, post-discovery, mid-session, uncommitted work) and guides users to the right command or team for their goal. Includes team routing table, 4 contextual flows, and decision guidance for when users don't know which team to use. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * refactor(commands): add Arguments and State Management sections to /start Addresses TEAMFORGE validation findings: - Add dedicated Arguments section documenting $ARGUMENTS handling - Add State Management section (reads/writes inventory) - Fix frontmatter: remove misleading generated_by field - Add explicit "manually authored" comment header https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): add /start to spec and template for cross-repo generation Moves /start from a hand-authored command to a proper spec-driven, sync-generated command available to any repo that adopts AgentKit Forge. - Add start command definition to commands.yaml (no feature gate — always on) - Create start.md template in .agentkit/templates/claude/commands/ - Add /start to CLAUDE.md Quick Reference table template https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after adding /start command Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(commands): make /start team routing dynamic instead of hardcoded Replace the static team routing table with dynamic discovery: 1. Read AGENT_TEAMS.md (from /discover) at runtime 2. Fall back to .agentkit/spec/teams.yaml 3. Fall back to /team-* command frontmatter This ensures /start always reflects the actual teams configured in any repo, rather than a hardcoded list that could go stale. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore(sync): regenerate outputs after dynamic routing change Generated by: pnpm -C .agentkit agentkit:sync https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add interactive TUI entry point with hybrid UI Replace static markdown output with an ink-based terminal UI that combines two modes: a guided conversation flow for first-run users and a fuzzy-searchable command palette for returning users. A persistent status bar shows repo state at a glance (branch, phase, backlog count, working tree status). - Context detection module mirrors /start Phase 1 signals - ConversationFlow: branching dialogue tree (choose-your-own-adventure) - CommandPalette: fuzzy search with context-ranked star recommendations - StatusBar: tmux-style persistent strip with color-coded segments - Supports --json flag for scripting/piping https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * feat(start): add test suite, error handling, and refactor for production readiness - Add vitest test infrastructure with 102 tests across 7 files - Coverage: 95.58% statements, 90.81% branches, 96.72% functions - Extract conversation tree to separate config module for testability - Add error boundary to App component for graceful error display - Add --help flag with usage documentation - Add TTY detection with JSON fallback for non-interactive environments - Add SIGINT/SIGTERM signal handling for clean exit https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore: add coverage to gitignore, include plan and workspace config https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — unused code, git cwd, magic numbers - Call exit() after command selection so Ink process terminates - Remove unused ctx prop from Header component - Fix git commands to use -C flag with root path parameter - Extract dumpContextJson() helper to deduplicate JSON output logic - Add comment explaining hardcoded team filter exclusion - Replace magic numbers with named constants (FUSE_THRESHOLD, RECOMMENDED_SCORE, MAX_BRANCH_LENGTH) - Remove unused ink-spinner dependency - Add test verifying git -C flag passes root correctly https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * fix(start): address review findings — security, correctness, test quality - CRITICAL: Replace execSync shell interpolation with execFileSync to prevent command injection via root parameter in detect.js - CRITICAL: Remove phantom --external:ink-spinner from build script and switch npx to direct esbuild invocation - HIGH: Fix exit race condition — use useEffect instead of setTimeout - HIGH: Wire up onSelect callback in ConversationFlow so Guide mode triggers the result screen in App - HIGH: Destructure and accept ctx prop in ConversationFlow - HIGH: Add back-navigation (Escape) in ConversationFlow - HIGH: Guard against undefined team.focus in commands.js tags - MEDIUM: Use functional setCursor form to avoid stale closures - MEDIUM: Key commandIndices Map by string id instead of object identity - MEDIUM: Improve parseTeams header detection (drop first row approach) - MEDIUM: Filter completed/done/closed items from backlogCount - MEDIUM: Extract shared makeCtx test utility across all test files - MEDIUM: Add null guard to StatusBar truncate helper - LOW: Validate orchestratorPhase is a number in range 1-5 - LOW: Fix pnpm-workspace.yaml list syntax - Replace all setTimeout in tests with vi.waitFor deterministic waits https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * test(start): add coverage for result screen exit path Add App-level test that navigates through ConversationFlow to a leaf node and verifies the result screen text is rendered before exit(). Confirms the synchronous useEffect exit is safe — React commits the render (Ink captures the frame) before useEffect fires. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW * chore: update generated sync output timestamps Generated files updated with current sync date from dev merge. https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW --------- * fix: caldues heuristics (#398) --------- Co-authored-by: Claude <noreply@anthropic.com> * fix(quality): resolve all lint and format errors - Fix Prettier formatting across engine src and start components - Resolve 381 markdown lint errors (MD040, MD024, MD036, MD029, MD022, MD001) - Add markdownlint config rules for intentional doc patterns - Add .claude/worktrees to prettierignore to exclude external branches - Enable markdownlint MD024/MD026 for duplicate headings and trailing colons All quality checks now pass: Prettier (0 errors), Markdown lint (0 errors), Tests (111/111), Build (28.9kb) * I'll update the last_updated field in all the files from '2026-03-12' to '2026-03-13'. This appears to be a routine timestamp update across all the AgentKit Forge generated files. * docs: add AgentKit Forge sync feedback Add detailed feedback on AgentKit Forge v3.1.0 integration, focusing on: - Windows line-ending issues and multi-editor sync behavior - Documentation scaffold-once limitations and override challenges - Unresolved placeholder warnings lacking diagnostics - Windows-specific pnpm execution problems * docs: update CLAUDE.md with repository-specific editing guidelines Clarified that modifications to `.agentkit` files are permitted in the agentkit-forge repository, while upstream directories remain protected. This ensures users understand the editing boundaries for project configuration and template files. * docs(claude): allow .agentkit edits in this repo (NB for framework dev) Made-with: Cursor * chore(sync): regenerate outputs after agentkit:sync Made-with: Cursor --------- Co-authored-by: Claude <noreply@anthropic.com> * chore(sync): regenerate outputs and update timestamps (#429) * Add start command: new user entry point with state detection (#387) * fix(commands): add AskUserQuestion to VALID_TOOLS and /start command The /start command session got stuck because AskUserQuestion was not included in the allowed-tools whitelist. This fix addresses three issues: 1. VALID_TOOLS in spec-validator was missing AskUserQuestion, TodoWrite, Agent, and NotebookEdit — preventing commands from declaring these Claude Code built-in tools in their allowed-tools. 2. The /start command template now explicitly includes AskUserQuestion in its allowed-tools frontmatter and instructs the agent to use it for interactive guided choices (Phase 3). 3. Added /start command spec to commands.yaml with AskUserQuestion as a declared tool dependency. Also adds a test case validating all four newly-added tools are accepted by the spec validator. https://claude.ai/code/session_01Qh3Xk3jFkVdeRAXTqLvq3M * fix(commands): remove unrendered Handlebars comment from start.md output The generated .claude/commands/start.md contained a raw {{! ... }} Handlebars comment that was not processed by the sync engine. Remove it so the generated output is clean Markdown. https://claude.ai/code/session_01Qh3Xk3jFkVdeRAXTqLvq3M --------- Co-authored-by: Claude <noreply@anthropic.com> * Add configurable prefix to kits commands (#388) * feat(sync): add configurable command prefix for generated slash commands Add `commandPrefix` setting to overlay settings that namespaces all generated slash commands across platforms: - Claude Code: subdirectory strategy (kits/check.md → /project:kits:check) - Cursor/Windsurf/Copilot/Codex: filename prefix (kits-check.md → /kits-check) - Team commands excluded from prefixing (already namespaced) Changes: - Add resolveCommandPath() helper with subdirectory/filename strategies - Update syncClaudeCommands, syncClaudeSkills, syncCursorCommands, syncWindsurfCommands, syncCopilotPrompts, sy…
Resolves 486 merge conflicts: - Generated files (.agents/skills/, .claude/, .cursor/, .windsurf/, .clinerules/, .roo/, .github/): accepted main (upstream) version per agentkit-generated merge driver convention - check.mjs: kept dev's robust PM detection (lockfile + commandExists verification) over main's simpler detectPackageManager helper; retained more informative warning message from dev - cli.mjs: kept dev's Array.isArray safety check for --help short-circuit Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Resolves conflicts from reverse-merge PR #437 (main → dev). Main had 2 commits that dev was missing: - chore(issues): update follow-up issues after kit-based domain filtering (#435) - feat(rename): rebrand CLI from agentkit to retort with deprecated alias (#436) Conflict resolution strategy: - Engine source files (.mjs): keep dev version (more complete — has domain filtering, backward-compat header checks, kit detection in init.mjs) - Template files: keep dev version (fixes "an Retort" → "a Retort" grammar) - .github/ISSUES/006: take main's ## Resolution section (phase 5 work) - .github/ISSUES/040: keep dev's Retort branding + add main's ## Resolution Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* Add start command: new user entry point with state detection (#387)
* fix(commands): add AskUserQuestion to VALID_TOOLS and /start command
The /start command session got stuck because AskUserQuestion was not
included in the allowed-tools whitelist. This fix addresses three issues:
1. VALID_TOOLS in spec-validator was missing AskUserQuestion, TodoWrite,
Agent, and NotebookEdit — preventing commands from declaring these
Claude Code built-in tools in their allowed-tools.
2. The /start command template now explicitly includes AskUserQuestion
in its allowed-tools frontmatter and instructs the agent to use it
for interactive guided choices (Phase 3).
3. Added /start command spec to commands.yaml with AskUserQuestion as
a declared tool dependency.
Also adds a test case validating all four newly-added tools are accepted
by the spec validator.
https://claude.ai/code/session_01Qh3Xk3jFkVdeRAXTqLvq3M
* fix(commands): remove unrendered Handlebars comment from start.md output
The generated .claude/commands/start.md contained a raw {{! ... }}
Handlebars comment that was not processed by the sync engine. Remove it
so the generated output is clean Markdown.
https://claude.ai/code/session_01Qh3Xk3jFkVdeRAXTqLvq3M
---------
* Add configurable prefix to kits commands (#388)
* feat(sync): add configurable command prefix for generated slash commands
Add `commandPrefix` setting to overlay settings that namespaces all
generated slash commands across platforms:
- Claude Code: subdirectory strategy (kits/check.md → /project:kits:check)
- Cursor/Windsurf/Copilot/Codex: filename prefix (kits-check.md → /kits-check)
- Team commands excluded from prefixing (already namespaced)
Changes:
- Add resolveCommandPath() helper with subdirectory/filename strategies
- Update syncClaudeCommands, syncClaudeSkills, syncCursorCommands,
syncWindsurfCommands, syncCopilotPrompts, syncCodexSkills
- Add commandPrefix to vars from overlay settings
- Add commandPrefixedName to buildCommandVars
- Add 16 unit + integration tests (all pass, 93 existing tests unaffected)
Default is null (no prefix) for full backwards compatibility.
https://claude.ai/code/session_01EBjmVEhi7fP2huAL3SBR6p
* fix(sync): address review findings for command prefix
- Remove unused afterAll import from test file
- Add clarifying comment that non-spec command files are also prefixed
- Add 2 integration tests verifying commandPrefixedName template variable
renders correctly with and without prefix
https://claude.ai/code/session_01EBjmVEhi7fP2huAL3SBR6p
---------
* fix(ci): CI remediation — package manager, review findings, test stability (#390)
* fix(ci): resolve 7 bugs from project review
- BUG-001: Replace flaky discover test with controlled temp fixture
- BUG-002: Run prettier --write to fix formatting drift
- BUG-003: Add form-template detection skip in issue label validation
- BUG-005: Change claude.yml to self-hosted runner
- BUG-006: Align branch protection required status checks with project.yaml
- BUG-007: Fix command injection in resolve-merge.sh (use grep -F)
* docs: update changelog, add planning registry review findings
- Add changelog entries for Wave 1-3 fixes (Added/Changed/Fixed/Removed)
- Add Project Review Findings section to planning registry (PR-001 to PR-014)
- Update planning docs after sync merge
* feat(review): add --generate-plans flag to project-review command
Add Phase 2.5 plan generation after project review findings. When
--generate-plans is passed (default: true), scaffold plan files from
critical/high findings into docs/planning/review-findings/.
Also includes sync cleanup of stale cursor/windsurf settings.
* chore(sync): regenerate all outputs after project review fixes
* feat(cli): dynamic flag loading from commands.yaml + context-aware template hook
- Replace ~200 lines of hardcoded VALID_FLAGS/FLAG_TYPES with loadCommandFlags()
that reads flag definitions from commands.yaml at startup
- CLI_INTERNAL_FLAGS/CLI_INTERNAL_FLAG_TYPES cover commands not in commands.yaml
- Self-validation warns at startup if any flag is missing a type definition
- Update cli.test.mjs to validate CLI_INTERNAL_FLAGS consistency
- Fix scaffold-once orphan bug: carry forward manifest entries for files
skipped by scaffold-once so orphan cleanup does not delete them
- Make protect-templates hook context-aware: skip protection in the
agentkit-forge source repo (detected via package.json name) so
maintainer agents can edit templates; block only in downstream repos
* feat(sync): add managed-mode script templates for downstream repos
Add 14 script templates (.agentkit/templates/scripts/) with `managed`
scaffold mode so downstream repos receive script updates via three-way
merge while preserving local customizations.
Templates include: create-doc, update-changelog, validate-documentation,
validate-numbering, check-documentation-requirement, sync-issues,
sync-split-pr, setup-agentkit-branch-governance, and resolve-merge
(both .sh and .ps1 variants where applicable).
Parameterized templates use {{defaultBranch}} and branch protection
variables from project.yaml. Engine wired via syncScripts() under
doc-scaffolding feature gate.
* feat(teams): add TeamForge meta-team for agent team creation (cogmesh #130)
Add the TEAMFORGE meta-team (T11) — a structured pipeline for creating,
validating, and deploying new agent team specifications. Adapted from
cogmesh #130 with a simplified 6-agent pipeline:
- input-clarifier: assess requests, extract constraints
- mission-definer: lock team definition (ID, scope, accepts)
- role-architect: design agent roles and dependencies
- prompt-engineer: write agent descriptions and rules
- flow-designer: design team command and integration points
- team-validator: quality gate for spec consistency
Includes /team-forge command with --task flag (create-team, validate-team,
audit-teams, update-team) and planning doc.
* feat(teams): add Strategic Ops team for cross-project coordination
Add the STRATEGIC OPS team (T12) — handles framework governance,
portfolio analysis, adoption strategy, impact assessment, and release
coordination across all repos using AgentKit Forge.
5-agent pipeline:
- portfolio-analyst: inventory repos, detect drift, adoption metrics
- governance-advisor: versioning strategy, breaking change protocols
- adoption-strategist: onboarding, migration paths, rollout plans
- impact-assessor: blast radius analysis for template/spec changes
- release-coordinator: version bumps, sync waves, release comms
Includes /team-strategic-ops command with --task and --scope flags.
* feat(agents): add agent/team relationship matrix analysis engine + scripts
Add comprehensive agent/team relationship analysis with 8 cross-reference
matrices and 10 supplementary analyses (orphans, cycles, bottlenecks,
reachability, critical path, notification amplifiers, etc.).
- Fix YAML structure: strategic-ops agents now under own top-level key
- Add explicit agents: lists to forge + strategic-ops teams in teams.yaml
- Add consolidation detection responsibilities to portfolio-analyst
- Create agent-analysis.mjs engine module (loadFullAgentGraph + renderers)
- Wire analyze-agents CLI command with --output/--matrix/--format flags
- Add managed-scaffold script templates (bash + PowerShell)
- Integrate into sync pipeline (auto-regenerates matrix on spec changes)
- Add 33 tests covering all matrices, analyses, and edge cases
* chore: update documentation files and add plan template
- Add trailing newlines to Cursor command documentation files for consistency
- Add new plan template files for project planning
- Improve markdown table formatting in Claude skills documentation
- Remove obsolete .clinerules/testing.md file
- Update various rule files with better formatting and advisory rule alignment
* feat(agents): add spec-compliance-auditor feedback loop + Cost Ops team (T14)
- Add spec-compliance-auditor to operations category (quality team) — closes
the feedback loop between agent specs and actual behavior
- Add Cost Ops team (T14) with 5 agents: model-economist,
token-efficiency-engineer, vendor-arbitrage-analyst, grant-hunter,
cost-ops-monitor
- Add ai-cost-ops rules domain with 6 conventions (model routing, token
budgets, caching, batch APIs, vendor abstraction, credit tracking)
- Add team-cost-ops command with --task, --period, --provider flags
- Update notification chains: data→cost-ops-monitor, infra→model-economist,
retrospective-analyst→spec-compliance-auditor
- Add intake routes: cost-ops, agent-performance
* fix(teams): add implement to cost-ops team accepts list
Resolves agent/team accepts mismatch — token-efficiency-engineer accepts
implement but the team definition only had investigate/review/plan/document.
* feat(cost-ops): add multi-provider infra cost ticket to backlog
Add detailed planning ticket for multi-provider infrastructure cost
normalisation, routing, and cost-agent integration. Covers 9 providers
(Anthropic, OpenAI, Google, Mistral, Cohere, self-hosted, Azure, AWS,
GCP) with 3-phase delivery plan and cross-team dependency tracking.
* fix(templates): resolve PR review comments from CodeRabbit
- Fix protect-templates.sh: package name check uses correct
"agentkit-forge-runtime" instead of "agentkit-forge"
- Fix protect-templates.ps1: malformed path (missing separator before
.agentkit) and same package name correction
- Fix update-changelog.ps1: change .mjs to .cjs to match CommonJS
require() syntax used in the inline Node script
- Fix resolve-merge.sh: add fallback for {{defaultBranch}} placeholder
- Fix AGENT_TEAMS.md: resolve three-way merge conflict markers left
by sync engine, keeping user formatting + implement in cost-ops
* feat(cost-ops): add WebSearch/WebFetch tools to cost-ops agents
Enable web research capabilities for cost-ops team:
- Add WebSearch and WebFetch to /team-cost-ops allowed-tools
- Add WebSearch and WebFetch to model-economist, vendor-arbitrage-analyst,
and grant-hunter agent preferred-tools
- Add web intake expansion ticket (P2) for MCP crawler, Puppeteer
integration, automated pricing refresh, and cross-session persistence
- Regenerate sync outputs
* feat(cost-ops): add Cost Ops team, agents, and multi-provider cost ticket (#364)
* feat(agents): add spec-compliance-auditor feedback loop + Cost Ops team (T14)
- Add spec-compliance-auditor to operations category (quality team) — closes
the feedback loop between agent specs and actual behavior
- Add Cost Ops team (T14) with 5 agents: model-economist,
token-efficiency-engineer, vendor-arbitrage-analyst, grant-hunter,
cost-ops-monitor
- Add ai-cost-ops rules domain with 6 conventions (model routing, token
budgets, caching, batch APIs, vendor abstraction, credit tracking)
- Add team-cost-ops command with --task, --period, --provider flags
- Update notification chains: data→cost-ops-monitor, infra→model-economist,
retrospective-analyst→spec-compliance-auditor
- Add intake routes: cost-ops, agent-performance
* fix(teams): add implement to cost-ops team accepts list
Resolves agent/team accepts mismatch — token-efficiency-engineer accepts
implement but the team definition only had investigate/review/plan/document.
* feat(cost-ops): add multi-provider infra cost ticket to backlog
Add detailed planning ticket for multi-provider infrastructure cost
normalisation, routing, and cost-agent integration. Covers 9 providers
(Anthropic, OpenAI, Google, Mistral, Cohere, self-hosted, Azure, AWS,
GCP) with 3-phase delivery plan and cross-team dependency tracking.
* fix(templates): resolve PR review comments from CodeRabbit
- Fix protect-templates.sh: package name check uses correct
"agentkit-forge-runtime" instead of "agentkit-forge"
- Fix protect-templates.ps1: malformed path (missing separator before
.agentkit) and same package name correction
- Fix update-changelog.ps1: change .mjs to .cjs to match CommonJS
require() syntax used in the inline Node script
- Fix resolve-merge.sh: add fallback for {{defaultBranch}} placeholder
- Fix AGENT_TEAMS.md: resolve three-way merge conflict markers left
by sync engine, keeping user formatting + implement in cost-ops
* feat(cost-ops): add WebSearch/WebFetch tools to cost-ops agents (#365)
Enable web research capabilities for cost-ops team:
- Add WebSearch and WebFetch to /team-cost-ops allowed-tools
- Add WebSearch and WebFetch to model-economist, vendor-arbitrage-analyst,
and grant-hunter agent preferred-tools
- Add web intake expansion ticket (P2) for MCP crawler, Puppeteer
integration, automated pricing refresh, and cross-session persistence
- Regenerate sync outputs
---------
* fix(teams): address CodeRabbit review findings on strategic-ops PR
- Lazy-load js-yaml in cli.mjs after ensureDependencies() to prevent
crash when node_modules is missing
- Convert YAML frontmatter to PowerShell comment blocks in all 6 PS1
templates to fix invalid PowerShell syntax
- Fix protect-templates hook path: use 3 parent traversals to reach
.agentkit/package.json from hooks directory
- Remove schema-invalid 'phase' field from ai-cost-ops rule domain
- Narrow strategic-ops scope: replace **/* catch-all with specific files
- Add strategic-ops to cost-ops handoff-chain for consistency
- Add Write tool to spec-compliance-auditor, vendor-arbitrage-analyst,
and grant-hunter agents
- Fix glob matching in resolve-merge.sh (use regex instead of broken
sed strip)
- Add merge failure vs conflict detection in resolve-merge.ps1
- Add branch existence check in setup-agentkit-branch-governance scripts
- Add gh CLI preflight check in sync-split-pr.ps1
- Deduplicate branch protection loop when defaultBranch is 'main'
- Fix applies-to glob: docs/planning/cost/** → docs/planning/cost-governance/**
- Fix non-canonical doc paths in intake-agent-proposal.md
- Add changelog entries for new teams, agents, and analysis engine
- Resolve AGENT_TEAMS.md merge conflict (accept narrowed scope)
- Run prettier on all modified files
* fix(templates): add gh auth preflight and changelog divider handling
- sync-split-pr.ps1: add gh auth status check before side effects
- update-changelog.ps1: stop before --- divider when appending entries
Addresses CodeRabbit review comments #7 and #13 on PR #356.
* fix(sync): set executable permission on analyze-agents.sh
Linux CI sync produces +x permissions; align local to match.
* fix(templates): address CodeRabbit review round 3-4 findings
- Fix YAML frontmatter in copilot agent template: use double quotes
for description field to handle apostrophes (CRITICAL)
- Fix protect-templates.sh/ps1 path traversal: correct parent
directory count for .agentkit/package.json source repo detection
- Add $PSNativeCommandUseErrorActionPreference to sync-split-pr.ps1
so native command failures (git, pnpm, gh) are treated as fatal
- Replace try/catch with $LASTEXITCODE check for gh auth status
- Deduplicate branch loop in setup-agentkit-branch-governance.sh
when defaultBranch equals 'main'
- Fix duplicate verification echo lines in governance scripts
* style(docs): fix prettier formatting on planning documents
Run prettier --write on web-intake-expansion.md and
intake-agent-proposal.md to fix CI formatting check.
* fix(tests): isolate render target gating tests with fresh temp dirs
Tests in the "render target gating" describe block shared a single temp
directory via beforeAll/afterAll. The first test ran --only claude
(generating .claude/ files), and the second ran --only warp expecting no
Claude files — but leftovers from test 1 caused the assertion to fail.
Changing to beforeEach/afterEach gives each test a clean directory.
Closes #377
* feat(commands): add /start command as new user entry point
Adds a context-aware triage command that detects repository state
(fresh clone, post-discovery, mid-session, uncommitted work) and
guides users to the right command or team for their goal.
Includes team routing table, 4 contextual flows, and decision
guidance for when users don't know which team to use.
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* refactor(commands): add Arguments and State Management sections to /start
Addresses TEAMFORGE validation findings:
- Add dedicated Arguments section documenting $ARGUMENTS handling
- Add State Management section (reads/writes inventory)
- Fix frontmatter: remove misleading generated_by field
- Add explicit "manually authored" comment header
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* feat(commands): add /start to spec and template for cross-repo generation
Moves /start from a hand-authored command to a proper spec-driven,
sync-generated command available to any repo that adopts AgentKit Forge.
- Add start command definition to commands.yaml (no feature gate — always on)
- Create start.md template in .agentkit/templates/claude/commands/
- Add /start to CLAUDE.md Quick Reference table template
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* chore(sync): regenerate outputs after adding /start command
Generated by: pnpm -C .agentkit agentkit:sync
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* feat(commands): make /start team routing dynamic instead of hardcoded
Replace the static team routing table with dynamic discovery:
1. Read AGENT_TEAMS.md (from /discover) at runtime
2. Fall back to .agentkit/spec/teams.yaml
3. Fall back to /team-* command frontmatter
This ensures /start always reflects the actual teams configured
in any repo, rather than a hardcoded list that could go stale.
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* chore(sync): regenerate outputs after dynamic routing change
Generated by: pnpm -C .agentkit agentkit:sync
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* feat(start): add interactive TUI entry point with hybrid UI
Replace static markdown output with an ink-based terminal UI that
combines two modes: a guided conversation flow for first-run users
and a fuzzy-searchable command palette for returning users. A
persistent status bar shows repo state at a glance (branch, phase,
backlog count, working tree status).
- Context detection module mirrors /start Phase 1 signals
- ConversationFlow: branching dialogue tree (choose-your-own-adventure)
- CommandPalette: fuzzy search with context-ranked star recommendations
- StatusBar: tmux-style persistent strip with color-coded segments
- Supports --json flag for scripting/piping
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* feat(start): add test suite, error handling, and refactor for production readiness
- Add vitest test infrastructure with 102 tests across 7 files
- Coverage: 95.58% statements, 90.81% branches, 96.72% functions
- Extract conversation tree to separate config module for testability
- Add error boundary to App component for graceful error display
- Add --help flag with usage documentation
- Add TTY detection with JSON fallback for non-interactive environments
- Add SIGINT/SIGTERM signal handling for clean exit
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* chore: add coverage to gitignore, include plan and workspace config
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* fix(start): address review findings — unused code, git cwd, magic numbers
- Call exit() after command selection so Ink process terminates
- Remove unused ctx prop from Header component
- Fix git commands to use -C flag with root path parameter
- Extract dumpContextJson() helper to deduplicate JSON output logic
- Add comment explaining hardcoded team filter exclusion
- Replace magic numbers with named constants (FUSE_THRESHOLD,
RECOMMENDED_SCORE, MAX_BRANCH_LENGTH)
- Remove unused ink-spinner dependency
- Add test verifying git -C flag passes root correctly
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* fix(start): address review findings — security, correctness, test quality
- CRITICAL: Replace execSync shell interpolation with execFileSync to
prevent command injection via root parameter in detect.js
- CRITICAL: Remove phantom --external:ink-spinner from build script and
switch npx to direct esbuild invocation
- HIGH: Fix exit race condition — use useEffect instead of setTimeout
- HIGH: Wire up onSelect callback in ConversationFlow so Guide mode
triggers the result screen in App
- HIGH: Destructure and accept ctx prop in ConversationFlow
- HIGH: Add back-navigation (Escape) in ConversationFlow
- HIGH: Guard against undefined team.focus in commands.js tags
- MEDIUM: Use functional setCursor form to avoid stale closures
- MEDIUM: Key commandIndices Map by string id instead of object identity
- MEDIUM: Improve parseTeams header detection (drop first row approach)
- MEDIUM: Filter completed/done/closed items from backlogCount
- MEDIUM: Extract shared makeCtx test utility across all test files
- MEDIUM: Add null guard to StatusBar truncate helper
- LOW: Validate orchestratorPhase is a number in range 1-5
- LOW: Fix pnpm-workspace.yaml list syntax
- Replace all setTimeout in tests with vi.waitFor deterministic waits
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* feat(engine): add pre-sync commit guard and interactive apply mode
Adds two safety features to the sync pipeline:
1. Pre-sync commit guard: Detects uncommitted changes in protected
directories (.agentkit/engines, spec, overlays) before sync runs.
In TTY mode, prompts to abort, stash, or continue. In non-TTY
mode (CI), prints a warning and proceeds.
2. Interactive apply mode: After rendering, shows a change summary
and prompts: apply all / skip all / prompt each file. Per-file
prompt supports show-diff and apply-all-remaining. Default in
TTY; bypassed with --yes, --no-prompt, or --force.
New module: sync-guard.mjs with 4 exported functions and 7 tests.
New CLI flags: --yes, --no-prompt for non-interactive sync.
* chore(sync): regenerate outputs after branch merges
* chore(sync): regenerate outputs after merge of new-user-entry-point
* feat(engine): add configurable package manager and fix review findings
- Add `stack.packageManager` field to project.yaml (pnpm | npm | yarn)
- Derive helper template vars (pmInstall, pmRun, pmExec, pmLockfile, etc.)
- Update CLAUDE.md template and hook/workflow templates to use {{packageManager}}
- Fix sync-guard to exclude .agentkit/spec from protected dirs and add try/catch
- Remove duplicate cost-ops team definition from teams.yaml
- Pin all dependency versions in package.json (remove ^ prefixes)
- Add vitest coverage thresholds (80% statements/branches/functions/lines)
- Fix src/start/ code quality: null guards, exit delay, error boundaries
- Harden consolidate-branches.sh: self-resolution guard, stash restore
- Regenerate all 533 output files via agentkit sync
* chore(engine): add brand color palette variables to sync vars
* fix(ci): fix test race condition, workspace config, and lockfile
- Fix ConversationFlow test: wait for 'Got it' before asserting hint text
- Add packages field to pnpm-workspace.yaml for proper workspace resolution
- Regenerate lockfile after version pinning (removed ^ prefixes)
- Remove accidental .agentkit/templates/src/ artifacts
* fix(start): add event loop yields to ConversationFlow tests
ink-select-input needs setImmediate yields after a new menu renders
before it can process ENTER keypresses. Without this, the second ENTER
in leaf-selection tests was swallowed, causing intermittent failures.
---------
* fix(spec): correct githubSlug to phoenixvc/agentkit-forge (#391)
* Add entry point for new framework users (#389)
* feat(commands): add /start command as new user entry point
Adds a context-aware triage command that detects repository state
(fresh clone, post-discovery, mid-session, uncommitted work) and
guides users to the right command or team for their goal.
Includes team routing table, 4 contextual flows, and decision
guidance for when users don't know which team to use.
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* refactor(commands): add Arguments and State Management sections to /start
Addresses TEAMFORGE validation findings:
- Add dedicated Arguments section documenting $ARGUMENTS handling
- Add State Management section (reads/writes inventory)
- Fix frontmatter: remove misleading generated_by field
- Add explicit "manually authored" comment header
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* feat(commands): add /start to spec and template for cross-repo generation
Moves /start from a hand-authored command to a proper spec-driven,
sync-generated command available to any repo that adopts AgentKit Forge.
- Add start command definition to commands.yaml (no feature gate — always on)
- Create start.md template in .agentkit/templates/claude/commands/
- Add /start to CLAUDE.md Quick Reference table template
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* chore(sync): regenerate outputs after adding /start command
Generated by: pnpm -C .agentkit agentkit:sync
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* feat(commands): make /start team routing dynamic instead of hardcoded
Replace the static team routing table with dynamic discovery:
1. Read AGENT_TEAMS.md (from /discover) at runtime
2. Fall back to .agentkit/spec/teams.yaml
3. Fall back to /team-* command frontmatter
This ensures /start always reflects the actual teams configured
in any repo, rather than a hardcoded list that could go stale.
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* chore(sync): regenerate outputs after dynamic routing change
Generated by: pnpm -C .agentkit agentkit:sync
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* feat(start): add interactive TUI entry point with hybrid UI
Replace static markdown output with an ink-based terminal UI that
combines two modes: a guided conversation flow for first-run users
and a fuzzy-searchable command palette for returning users. A
persistent status bar shows repo state at a glance (branch, phase,
backlog count, working tree status).
- Context detection module mirrors /start Phase 1 signals
- ConversationFlow: branching dialogue tree (choose-your-own-adventure)
- CommandPalette: fuzzy search with context-ranked star recommendations
- StatusBar: tmux-style persistent strip with color-coded segments
- Supports --json flag for scripting/piping
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* feat(start): add test suite, error handling, and refactor for production readiness
- Add vitest test infrastructure with 102 tests across 7 files
- Coverage: 95.58% statements, 90.81% branches, 96.72% functions
- Extract conversation tree to separate config module for testability
- Add error boundary to App component for graceful error display
- Add --help flag with usage documentation
- Add TTY detection with JSON fallback for non-interactive environments
- Add SIGINT/SIGTERM signal handling for clean exit
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* chore: add coverage to gitignore, include plan and workspace config
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* fix(start): address review findings — unused code, git cwd, magic numbers
- Call exit() after command selection so Ink process terminates
- Remove unused ctx prop from Header component
- Fix git commands to use -C flag with root path parameter
- Extract dumpContextJson() helper to deduplicate JSON output logic
- Add comment explaining hardcoded team filter exclusion
- Replace magic numbers with named constants (FUSE_THRESHOLD,
RECOMMENDED_SCORE, MAX_BRANCH_LENGTH)
- Remove unused ink-spinner dependency
- Add test verifying git -C flag passes root correctly
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* fix(start): address review findings — security, correctness, test quality
- CRITICAL: Replace execSync shell interpolation with execFileSync to
prevent command injection via root parameter in detect.js
- CRITICAL: Remove phantom --external:ink-spinner from build script and
switch npx to direct esbuild invocation
- HIGH: Fix exit race condition — use useEffect instead of setTimeout
- HIGH: Wire up onSelect callback in ConversationFlow so Guide mode
triggers the result screen in App
- HIGH: Destructure and accept ctx prop in ConversationFlow
- HIGH: Add back-navigation (Escape) in ConversationFlow
- HIGH: Guard against undefined team.focus in commands.js tags
- MEDIUM: Use functional setCursor form to avoid stale closures
- MEDIUM: Key commandIndices Map by string id instead of object identity
- MEDIUM: Improve parseTeams header detection (drop first row approach)
- MEDIUM: Filter completed/done/closed items from backlogCount
- MEDIUM: Extract shared makeCtx test utility across all test files
- MEDIUM: Add null guard to StatusBar truncate helper
- LOW: Validate orchestratorPhase is a number in range 1-5
- LOW: Fix pnpm-workspace.yaml list syntax
- Replace all setTimeout in tests with vi.waitFor deterministic waits
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* test(start): add coverage for result screen exit path
Add App-level test that navigates through ConversationFlow to a leaf
node and verifies the result screen text is rendered before exit().
Confirms the synchronous useEffect exit is safe — React commits the
render (Ink captures the frame) before useEffect fires.
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* chore: update generated sync output timestamps
Generated files updated with current sync date from dev merge.
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
---------
* fix: caldues heuristics (#398)
* feat: complete revisit of agents (#399) (#400)
* Add start command: new user entry point with state detection (#387)
* fix(commands): add AskUserQuestion to VALID_TOOLS and /start command
The /start command session got stuck because AskUserQuestion was not
included in the allowed-tools whitelist. This fix addresses three issues:
1. VALID_TOOLS in spec-validator was missing AskUserQuestion, TodoWrite,
Agent, and NotebookEdit — preventing commands from declaring these
Claude Code built-in tools in their allowed-tools.
2. The /start command template now explicitly includes AskUserQuestion
in its allowed-tools frontmatter and instructs the agent to use it
for interactive guided choices (Phase 3).
3. Added /start command spec to commands.yaml with AskUserQuestion as
a declared tool dependency.
Also adds a test case validating all four newly-added tools are accepted
by the spec validator.
https://claude.ai/code/session_01Qh3Xk3jFkVdeRAXTqLvq3M
* fix(commands): remove unrendered Handlebars comment from start.md output
The generated .claude/commands/start.md contained a raw {{! ... }}
Handlebars comment that was not processed by the sync engine. Remove it
so the generated output is clean Markdown.
https://claude.ai/code/session_01Qh3Xk3jFkVdeRAXTqLvq3M
---------
* Add configurable prefix to kits commands (#388)
* feat(sync): add configurable command prefix for generated slash commands
Add `commandPrefix` setting to overlay settings that namespaces all
generated slash commands across platforms:
- Claude Code: subdirectory strategy (kits/check.md → /project:kits:check)
- Cursor/Windsurf/Copilot/Codex: filename prefix (kits-check.md → /kits-check)
- Team commands excluded from prefixing (already namespaced)
Changes:
- Add resolveCommandPath() helper with subdirectory/filename strategies
- Update syncClaudeCommands, syncClaudeSkills, syncCursorCommands,
syncWindsurfCommands, syncCopilotPrompts, syncCodexSkills
- Add commandPrefix to vars from overlay settings
- Add commandPrefixedName to buildCommandVars
- Add 16 unit + integration tests (all pass, 93 existing tests unaffected)
Default is null (no prefix) for full backwards compatibility.
https://claude.ai/code/session_01EBjmVEhi7fP2huAL3SBR6p
* fix(sync): address review findings for command prefix
- Remove unused afterAll import from test file
- Add clarifying comment that non-spec command files are also prefixed
- Add 2 integration tests verifying commandPrefixedName template variable
renders correctly with and without prefix
https://claude.ai/code/session_01EBjmVEhi7fP2huAL3SBR6p
---------
* fix(ci): CI remediation — package manager, review findings, test stability (#390)
* fix(ci): resolve 7 bugs from project review
- BUG-001: Replace flaky discover test with controlled temp fixture
- BUG-002: Run prettier --write to fix formatting drift
- BUG-003: Add form-template detection skip in issue label validation
- BUG-005: Change claude.yml to self-hosted runner
- BUG-006: Align branch protection required status checks with project.yaml
- BUG-007: Fix command injection in resolve-merge.sh (use grep -F)
* docs: update changelog, add planning registry review findings
- Add changelog entries for Wave 1-3 fixes (Added/Changed/Fixed/Removed)
- Add Project Review Findings section to planning registry (PR-001 to PR-014)
- Update planning docs after sync merge
* feat(review): add --generate-plans flag to project-review command
Add Phase 2.5 plan generation after project review findings. When
--generate-plans is passed (default: true), scaffold plan files from
critical/high findings into docs/planning/review-findings/.
Also includes sync cleanup of stale cursor/windsurf settings.
* chore(sync): regenerate all outputs after project review fixes
* feat(cli): dynamic flag loading from commands.yaml + context-aware template hook
- Replace ~200 lines of hardcoded VALID_FLAGS/FLAG_TYPES with loadCommandFlags()
that reads flag definitions from commands.yaml at startup
- CLI_INTERNAL_FLAGS/CLI_INTERNAL_FLAG_TYPES cover commands not in commands.yaml
- Self-validation warns at startup if any flag is missing a type definition
- Update cli.test.mjs to validate CLI_INTERNAL_FLAGS consistency
- Fix scaffold-once orphan bug: carry forward manifest entries for files
skipped by scaffold-once so orphan cleanup does not delete them
- Make protect-templates hook context-aware: skip protection in the
agentkit-forge source repo (detected via package.json name) so
maintainer agents can edit templates; block only in downstream repos
* feat(sync): add managed-mode script templates for downstream repos
Add 14 script templates (.agentkit/templates/scripts/) with `managed`
scaffold mode so downstream repos receive script updates via three-way
merge while preserving local customizations.
Templates include: create-doc, update-changelog, validate-documentation,
validate-numbering, check-documentation-requirement, sync-issues,
sync-split-pr, setup-agentkit-branch-governance, and resolve-merge
(both .sh and .ps1 variants where applicable).
Parameterized templates use {{defaultBranch}} and branch protection
variables from project.yaml. Engine wired via syncScripts() under
doc-scaffolding feature gate.
* feat(teams): add TeamForge meta-team for agent team creation (cogmesh #130)
Add the TEAMFORGE meta-team (T11) — a structured pipeline for creating,
validating, and deploying new agent team specifications. Adapted from
cogmesh #130 with a simplified 6-agent pipeline:
- input-clarifier: assess requests, extract constraints
- mission-definer: lock team definition (ID, scope, accepts)
- role-architect: design agent roles and dependencies
- prompt-engineer: write agent descriptions and rules
- flow-designer: design team command and integration points
- team-validator: quality gate for spec consistency
Includes /team-forge command with --task flag (create-team, validate-team,
audit-teams, update-team) and planning doc.
* feat(teams): add Strategic Ops team for cross-project coordination
Add the STRATEGIC OPS team (T12) — handles framework governance,
portfolio analysis, adoption strategy, impact assessment, and release
coordination across all repos using AgentKit Forge.
5-agent pipeline:
- portfolio-analyst: inventory repos, detect drift, adoption metrics
- governance-advisor: versioning strategy, breaking change protocols
- adoption-strategist: onboarding, migration paths, rollout plans
- impact-assessor: blast radius analysis for template/spec changes
- release-coordinator: version bumps, sync waves, release comms
Includes /team-strategic-ops command with --task and --scope flags.
* feat(agents): add agent/team relationship matrix analysis engine + scripts
Add comprehensive agent/team relationship analysis with 8 cross-reference
matrices and 10 supplementary analyses (orphans, cycles, bottlenecks,
reachability, critical path, notification amplifiers, etc.).
- Fix YAML structure: strategic-ops agents now under own top-level key
- Add explicit agents: lists to forge + strategic-ops teams in teams.yaml
- Add consolidation detection responsibilities to portfolio-analyst
- Create agent-analysis.mjs engine module (loadFullAgentGraph + renderers)
- Wire analyze-agents CLI command with --output/--matrix/--format flags
- Add managed-scaffold script templates (bash + PowerShell)
- Integrate into sync pipeline (auto-regenerates matrix on spec changes)
- Add 33 tests covering all matrices, analyses, and edge cases
* chore: update documentation files and add plan template
- Add trailing newlines to Cursor command documentation files for consistency
- Add new plan template files for project planning
- Improve markdown table formatting in Claude skills documentation
- Remove obsolete .clinerules/testing.md file
- Update various rule files with better formatting and advisory rule alignment
* feat(agents): add spec-compliance-auditor feedback loop + Cost Ops team (T14)
- Add spec-compliance-auditor to operations category (quality team) — closes
the feedback loop between agent specs and actual behavior
- Add Cost Ops team (T14) with 5 agents: model-economist,
token-efficiency-engineer, vendor-arbitrage-analyst, grant-hunter,
cost-ops-monitor
- Add ai-cost-ops rules domain with 6 conventions (model routing, token
budgets, caching, batch APIs, vendor abstraction, credit tracking)
- Add team-cost-ops command with --task, --period, --provider flags
- Update notification chains: data→cost-ops-monitor, infra→model-economist,
retrospective-analyst→spec-compliance-auditor
- Add intake routes: cost-ops, agent-performance
* fix(teams): add implement to cost-ops team accepts list
Resolves agent/team accepts mismatch — token-efficiency-engineer accepts
implement but the team definition only had investigate/review/plan/document.
* feat(cost-ops): add multi-provider infra cost ticket to backlog
Add detailed planning ticket for multi-provider infrastructure cost
normalisation, routing, and cost-agent integration. Covers 9 providers
(Anthropic, OpenAI, Google, Mistral, Cohere, self-hosted, Azure, AWS,
GCP) with 3-phase delivery plan and cross-team dependency tracking.
* fix(templates): resolve PR review comments from CodeRabbit
- Fix protect-templates.sh: package name check uses correct
"agentkit-forge-runtime" instead of "agentkit-forge"
- Fix protect-templates.ps1: malformed path (missing separator before
.agentkit) and same package name correction
- Fix update-changelog.ps1: change .mjs to .cjs to match CommonJS
require() syntax used in the inline Node script
- Fix resolve-merge.sh: add fallback for {{defaultBranch}} placeholder
- Fix AGENT_TEAMS.md: resolve three-way merge conflict markers left
by sync engine, keeping user formatting + implement in cost-ops
* feat(cost-ops): add WebSearch/WebFetch tools to cost-ops agents
Enable web research capabilities for cost-ops team:
- Add WebSearch and WebFetch to /team-cost-ops allowed-tools
- Add WebSearch and WebFetch to model-economist, vendor-arbitrage-analyst,
and grant-hunter agent preferred-tools
- Add web intake expansion ticket (P2) for MCP crawler, Puppeteer
integration, automated pricing refresh, and cross-session persistence
- Regenerate sync outputs
* feat(cost-ops): add Cost Ops team, agents, and multi-provider cost ticket (#364)
* feat(agents): add spec-compliance-auditor feedback loop + Cost Ops team (T14)
- Add spec-compliance-auditor to operations category (quality team) — closes
the feedback loop between agent specs and actual behavior
- Add Cost Ops team (T14) with 5 agents: model-economist,
token-efficiency-engineer, vendor-arbitrage-analyst, grant-hunter,
cost-ops-monitor
- Add ai-cost-ops rules domain with 6 conventions (model routing, token
budgets, caching, batch APIs, vendor abstraction, credit tracking)
- Add team-cost-ops command with --task, --period, --provider flags
- Update notification chains: data→cost-ops-monitor, infra→model-economist,
retrospective-analyst→spec-compliance-auditor
- Add intake routes: cost-ops, agent-performance
* fix(teams): add implement to cost-ops team accepts list
Resolves agent/team accepts mismatch — token-efficiency-engineer accepts
implement but the team definition only had investigate/review/plan/document.
* feat(cost-ops): add multi-provider infra cost ticket to backlog
Add detailed planning ticket for multi-provider infrastructure cost
normalisation, routing, and cost-agent integration. Covers 9 providers
(Anthropic, OpenAI, Google, Mistral, Cohere, self-hosted, Azure, AWS,
GCP) with 3-phase delivery plan and cross-team dependency tracking.
* fix(templates): resolve PR review comments from CodeRabbit
- Fix protect-templates.sh: package name check uses correct
"agentkit-forge-runtime" instead of "agentkit-forge"
- Fix protect-templates.ps1: malformed path (missing separator before
.agentkit) and same package name correction
- Fix update-changelog.ps1: change .mjs to .cjs to match CommonJS
require() syntax used in the inline Node script
- Fix resolve-merge.sh: add fallback for {{defaultBranch}} placeholder
- Fix AGENT_TEAMS.md: resolve three-way merge conflict markers left
by sync engine, keeping user formatting + implement in cost-ops
* feat(cost-ops): add WebSearch/WebFetch tools to cost-ops agents (#365)
Enable web research capabilities for cost-ops team:
- Add WebSearch and WebFetch to /team-cost-ops allowed-tools
- Add WebSearch and WebFetch to model-economist, vendor-arbitrage-analyst,
and grant-hunter agent preferred-tools
- Add web intake expansion ticket (P2) for MCP crawler, Puppeteer
integration, automated pricing refresh, and cross-session persistence
- Regenerate sync outputs
---------
* fix(teams): address CodeRabbit review findings on strategic-ops PR
- Lazy-load js-yaml in cli.mjs after ensureDependencies() to prevent
crash when node_modules is missing
- Convert YAML frontmatter to PowerShell comment blocks in all 6 PS1
templates to fix invalid PowerShell syntax
- Fix protect-templates hook path: use 3 parent traversals to reach
.agentkit/package.json from hooks directory
- Remove schema-invalid 'phase' field from ai-cost-ops rule domain
- Narrow strategic-ops scope: replace **/* catch-all with specific files
- Add strategic-ops to cost-ops handoff-chain for consistency
- Add Write tool to spec-compliance-auditor, vendor-arbitrage-analyst,
and grant-hunter agents
- Fix glob matching in resolve-merge.sh (use regex instead of broken
sed strip)
- Add merge failure vs conflict detection in resolve-merge.ps1
- Add branch existence check in setup-agentkit-branch-governance scripts
- Add gh CLI preflight check in sync-split-pr.ps1
- Deduplicate branch protection loop when defaultBranch is 'main'
- Fix applies-to glob: docs/planning/cost/** → docs/planning/cost-governance/**
- Fix non-canonical doc paths in intake-agent-proposal.md
- Add changelog entries for new teams, agents, and analysis engine
- Resolve AGENT_TEAMS.md merge conflict (accept narrowed scope)
- Run prettier on all modified files
* fix(templates): add gh auth preflight and changelog divider handling
- sync-split-pr.ps1: add gh auth status check before side effects
- update-changelog.ps1: stop before --- divider when appending entries
Addresses CodeRabbit review comments #7 and #13 on PR #356.
* fix(sync): set executable permission on analyze-agents.sh
Linux CI sync produces +x permissions; align local to match.
* fix(templates): address CodeRabbit review round 3-4 findings
- Fix YAML frontmatter in copilot agent template: use double quotes
for description field to handle apostrophes (CRITICAL)
- Fix protect-templates.sh/ps1 path traversal: correct parent
directory count for .agentkit/package.json source repo detection
- Add $PSNativeCommandUseErrorActionPreference to sync-split-pr.ps1
so native command failures (git, pnpm, gh) are treated as fatal
- Replace try/catch with $LASTEXITCODE check for gh auth status
- Deduplicate branch loop in setup-agentkit-branch-governance.sh
when defaultBranch equals 'main'
- Fix duplicate verification echo lines in governance scripts
* style(docs): fix prettier formatting on planning documents
Run prettier --write on web-intake-expansion.md and
intake-agent-proposal.md to fix CI formatting check.
* fix(tests): isolate render target gating tests with fresh temp dirs
Tests in the "render target gating" describe block shared a single temp
directory via beforeAll/afterAll. The first test ran --only claude
(generating .claude/ files), and the second ran --only warp expecting no
Claude files — but leftovers from test 1 caused the assertion to fail.
Changing to beforeEach/afterEach gives each test a clean directory.
Closes #377
* feat(commands): add /start command as new user entry point
Adds a context-aware triage command that detects repository state
(fresh clone, post-discovery, mid-session, uncommitted work) and
guides users to the right command or team for their goal.
Includes team routing table, 4 contextual flows, and decision
guidance for when users don't know which team to use.
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* refactor(commands): add Arguments and State Management sections to /start
Addresses TEAMFORGE validation findings:
- Add dedicated Arguments section documenting $ARGUMENTS handling
- Add State Management section (reads/writes inventory)
- Fix frontmatter: remove misleading generated_by field
- Add explicit "manually authored" comment header
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* feat(commands): add /start to spec and template for cross-repo generation
Moves /start from a hand-authored command to a proper spec-driven,
sync-generated command available to any repo that adopts AgentKit Forge.
- Add start command definition to commands.yaml (no feature gate — always on)
- Create start.md template in .agentkit/templates/claude/commands/
- Add /start to CLAUDE.md Quick Reference table template
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* chore(sync): regenerate outputs after adding /start command
Generated by: pnpm -C .agentkit agentkit:sync
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* feat(commands): make /start team routing dynamic instead of hardcoded
Replace the static team routing table with dynamic discovery:
1. Read AGENT_TEAMS.md (from /discover) at runtime
2. Fall back to .agentkit/spec/teams.yaml
3. Fall back to /team-* command frontmatter
This ensures /start always reflects the actual teams configured
in any repo, rather than a hardcoded list that could go stale.
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* chore(sync): regenerate outputs after dynamic routing change
Generated by: pnpm -C .agentkit agentkit:sync
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* feat(start): add interactive TUI entry point with hybrid UI
Replace static markdown output with an ink-based terminal UI that
combines two modes: a guided conversation flow for first-run users
and a fuzzy-searchable command palette for returning users. A
persistent status bar shows repo state at a glance (branch, phase,
backlog count, working tree status).
- Context detection module mirrors /start Phase 1 signals
- ConversationFlow: branching dialogue tree (choose-your-own-adventure)
- CommandPalette: fuzzy search with context-ranked star recommendations
- StatusBar: tmux-style persistent strip with color-coded segments
- Supports --json flag for scripting/piping
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* feat(start): add test suite, error handling, and refactor for production readiness
- Add vitest test infrastructure with 102 tests across 7 files
- Coverage: 95.58% statements, 90.81% branches, 96.72% functions
- Extract conversation tree to separate config module for testability
- Add error boundary to App component for graceful error display
- Add --help flag with usage documentation
- Add TTY detection with JSON fallback for non-interactive environments
- Add SIGINT/SIGTERM signal handling for clean exit
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* chore: add coverage to gitignore, include plan and workspace config
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* fix(start): address review findings — unused code, git cwd, magic numbers
- Call exit() after command selection so Ink process terminates
- Remove unused ctx prop from Header component
- Fix git commands to use -C flag with root path parameter
- Extract dumpContextJson() helper to deduplicate JSON output logic
- Add comment explaining hardcoded team filter exclusion
- Replace magic numbers with named constants (FUSE_THRESHOLD,
RECOMMENDED_SCORE, MAX_BRANCH_LENGTH)
- Remove unused ink-spinner dependency
- Add test verifying git -C flag passes root correctly
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* fix(start): address review findings — security, correctness, test quality
- CRITICAL: Replace execSync shell interpolation with execFileSync to
prevent command injection via root parameter in detect.js
- CRITICAL: Remove phantom --external:ink-spinner from build script and
switch npx to direct esbuild invocation
- HIGH: Fix exit race condition — use useEffect instead of setTimeout
- HIGH: Wire up onSelect callback in ConversationFlow so Guide mode
triggers the result screen in App
- HIGH: Destructure and accept ctx prop in ConversationFlow
- HIGH: Add back-navigation (Escape) in ConversationFlow
- HIGH: Guard against undefined team.focus in commands.js tags
- MEDIUM: Use functional setCursor form to avoid stale closures
- MEDIUM: Key commandIndices Map by string id instead of object identity
- MEDIUM: Improve parseTeams header detection (drop first row approach)
- MEDIUM: Filter completed/done/closed items from backlogCount
- MEDIUM: Extract shared makeCtx test utility across all test files
- MEDIUM: Add null guard to StatusBar truncate helper
- LOW: Validate orchestratorPhase is a number in range 1-5
- LOW: Fix pnpm-workspace.yaml list syntax
- Replace all setTimeout in tests with vi.waitFor deterministic waits
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* feat(engine): add pre-sync commit guard and interactive apply mode
Adds two safety features to the sync pipeline:
1. Pre-sync commit guard: Detects uncommitted changes in protected
directories (.agentkit/engines, spec, overlays) before sync runs.
In TTY mode, prompts to abort, stash, or continue. In non-TTY
mode (CI), prints a warning and proceeds.
2. Interactive apply mode: After rendering, shows a change summary
and prompts: apply all / skip all / prompt each file. Per-file
prompt supports show-diff and apply-all-remaining. Default in
TTY; bypassed with --yes, --no-prompt, or --force.
New module: sync-guard.mjs with 4 exported functions and 7 tests.
New CLI flags: --yes, --no-prompt for non-interactive sync.
* chore(sync): regenerate outputs after branch merges
* chore(sync): regenerate outputs after merge of new-user-entry-point
* feat(engine): add configurable package manager and fix review findings
- Add `stack.packageManager` field to project.yaml (pnpm | npm | yarn)
- Derive helper template vars (pmInstall, pmRun, pmExec, pmLockfile, etc.)
- Update CLAUDE.md template and hook/workflow templates to use {{packageManager}}
- Fix sync-guard to exclude .agentkit/spec from protected dirs and add try/catch
- Remove duplicate cost-ops team definition from teams.yaml
- Pin all dependency versions in package.json (remove ^ prefixes)
- Add vitest coverage thresholds (80% statements/branches/functions/lines)
- Fix src/start/ code quality: null guards, exit delay, error boundaries
- Harden consolidate-branches.sh: self-resolution guard, stash restore
- Regenerate all 533 output files via agentkit sync
* chore(engine): add brand color palette variables to sync vars
* fix(ci): fix test race condition, workspace config, and lockfile
- Fix ConversationFlow test: wait for 'Got it' before asserting hint text
- Add packages field to pnpm-workspace.yaml for proper workspace resolution
- Regenerate lockfile after version pinning (removed ^ prefixes)
- Remove accidental .agentkit/templates/src/ artifacts
* fix(start): add event loop yields to ConversationFlow tests
ink-select-input needs setImmediate yields after a new menu renders
before it can process ENTER keypresses. Without this, the second ENTER
in leaf-selection tests was swallowed, causing intermittent failures.
---------
* fix(spec): correct githubSlug to phoenixvc/agentkit-forge (#391)
* Add entry point for new framework users (#389)
* feat(commands): add /start command as new user entry point
Adds a context-aware triage command that detects repository state
(fresh clone, post-discovery, mid-session, uncommitted work) and
guides users to the right command or team for their goal.
Includes team routing table, 4 contextual flows, and decision
guidance for when users don't know which team to use.
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* refactor(commands): add Arguments and State Management sections to /start
Addresses TEAMFORGE validation findings:
- Add dedicated Arguments section documenting $ARGUMENTS handling
- Add State Management section (reads/writes inventory)
- Fix frontmatter: remove misleading generated_by field
- Add explicit "manually authored" comment header
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* feat(commands): add /start to spec and template for cross-repo generation
Moves /start from a hand-authored command to a proper spec-driven,
sync-generated command available to any repo that adopts AgentKit Forge.
- Add start command definition to commands.yaml (no feature gate — always on)
- Create start.md template in .agentkit/templates/claude/commands/
- Add /start to CLAUDE.md Quick Reference table template
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* chore(sync): regenerate outputs after adding /start command
Generated by: pnpm -C .agentkit agentkit:sync
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* feat(commands): make /start team routing dynamic instead of hardcoded
Replace the static team routing table with dynamic discovery:
1. Read AGENT_TEAMS.md (from /discover) at runtime
2. Fall back to .agentkit/spec/teams.yaml
3. Fall back to /team-* command frontmatter
This ensures /start always reflects the actual teams configured
in any repo, rather than a hardcoded list that could go stale.
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* chore(sync): regenerate outputs after dynamic routing change
Generated by: pnpm -C .agentkit agentkit:sync
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* feat(start): add interactive TUI entry point with hybrid UI
Replace static markdown output with an ink-based terminal UI that
combines two modes: a guided conversation flow for first-run users
and a fuzzy-searchable command palette for returning users. A
persistent status bar shows repo state at a glance (branch, phase,
backlog count, working tree status).
- Context detection module mirrors /start Phase 1 signals
- ConversationFlow: branching dialogue tree (choose-your-own-adventure)
- CommandPalette: fuzzy search with context-ranked star recommendations
- StatusBar: tmux-style persistent strip with color-coded segments
- Supports --json flag for scripting/piping
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* feat(start): add test suite, error handling, and refactor for production readiness
- Add vitest test infrastructure with 102 tests across 7 files
- Coverage: 95.58% statements, 90.81% branches, 96.72% functions
- Extract conversation tree to separate config module for testability
- Add error boundary to App component for graceful error display
- Add --help flag with usage documentation
- Add TTY detection with JSON fallback for non-interactive environments
- Add SIGINT/SIGTERM signal handling for clean exit
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* chore: add coverage to gitignore, include plan and workspace config
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* fix(start): address review findings — unused code, git cwd, magic numbers
- Call exit() after command selection so Ink process terminates
- Remove unused ctx prop from Header component
- Fix git commands to use -C flag with root path parameter
- Extract dumpContextJson() helper to deduplicate JSON output logic
- Add comment explaining hardcoded team filter exclusion
- Replace magic numbers with named constants (FUSE_THRESHOLD,
RECOMMENDED_SCORE, MAX_BRANCH_LENGTH)
- Remove unused ink-spinner dependency
- Add test verifying git -C flag passes root correctly
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* fix(start): address review findings — security, correctness, test quality
- CRITICAL: Replace execSync shell interpolation with execFileSync to
prevent command injection via root parameter in detect.js
- CRITICAL: Remove phantom --external:ink-spinner from build script and
switch npx to direct esbuild invocation
- HIGH: Fix exit race condition — use useEffect instead of setTimeout
- HIGH: Wire up onSelect callback in ConversationFlow so Guide mode
triggers the result screen in App
- HIGH: Destructure and accept ctx prop in ConversationFlow
- HIGH: Add back-navigation (Escape) in ConversationFlow
- HIGH: Guard against undefined team.focus in commands.js tags
- MEDIUM: Use functional setCursor form to avoid stale closures
- MEDIUM: Key commandIndices Map by string id instead of object identity
- MEDIUM: Improve parseTeams header detection (drop first row approach)
- MEDIUM: Filter completed/done/closed items from backlogCount
- MEDIUM: Extract shared makeCtx test utility across all test files
- MEDIUM: Add null guard to StatusBar truncate helper
- LOW: Validate orchestratorPhase is a number in range 1-5
- LOW: Fix pnpm-workspace.yaml list syntax
- Replace all setTimeout in tests with vi.waitFor deterministic waits
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* test(start): add coverage for result screen exit path
Add App-level test that navigates through ConversationFlow to a leaf
node and verifies the result screen text is rendered before exit().
Confirms the synchronous useEffect exit is safe — React commits the
render (Ink captures the frame) before useEffect fires.
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
* chore: update generated sync output timestamps
Generated files updated with current sync date from dev merge.
https://claude.ai/code/session_01Gy1HvvywVe6Z2iFJ2bHYCW
---------
* fix: caldues heuristics (#398)
---------
* fix(quality): resolve all lint and format errors
- Fix Prettier formatting across engine src and start components
- Resolve 381 markdown lint errors (MD040, MD024, MD036, MD029, MD022, MD001)
- Add markdownlint config rules for intentional doc patterns
- Add .claude/worktrees to prettierignore to exclude external branches
- Enable markdownlint MD024/MD026 for duplicate headings and trailing colons
All quality checks now pass: Prettier (0 errors), Markdown lint (0 errors), Tests (111/111), Build (28.9kb)
* I'll update the last_updated field in all the files from '2026-03-12' to '2026-03-13'. This appears to be a routine timestamp update across all the AgentKit Forge generated files.
* docs: add AgentKit Forge sync feedback
Add detailed feedback on AgentKit Forge v3.1.0 integration, focusing on:
- Windows line-ending issues and multi-editor sync behavior
- Documentation scaffold-once limitations and override challenges
- Unresolved placeholder warnings lacking diagnostics
- Windows-specific pnpm execution problems
* docs: update CLAUDE.md with repository-specific editing guidelines
Clarified that modifications to `.agentkit` files are permitted in the agentkit-forge repository, while upstream directories remain protected. This ensures users understand the editing boundaries for project configuration and template files.
* docs(claude): allow .agentkit edits in this repo (NB for framework dev)
Made-with: Cursor
* chore(sync): regenerate outputs after agentkit:sync
Made-with: Cursor
* Fix/generated files and conflict markers (#427)
* fix(infra): resolve container app fqdn attribute and format code
* chore(sync): update AGENT_BACKLOG.md and other files for task management
- Enhanced AGENT_BACKLOG.md with detailed task scopes for CI pipeline configuration and test framework setup.
- Added new docker-compose.yml for local/staging validation of the framework.
- Updated CONTRIBUTING.md to include documentation hub link in the Discovery phase.
- Introduced README.md files in db, infra, and migrations directories to clarify their purpose for adopters.
- Added API conventions documentation to guide adopters on structuring their APIs.
- Created implementation plan for state management improvements and added relevant tests.
- Regenerated outputs across various files to reflect recent changes and ensure consistency.
* chore(ci): reduce CodeQL to weekly + manual only (#430)
* chore(ci): reduce CodeQL to weekly schedule + manual trigger
Removes push and pull_request triggers to reduce GitHub Actions costs.
Scans were running on every PR including Renovate dependency updates.
* Potential fix for pull request finding
---------
* docs(architecture): add tool-neutral agent hub findings, ADR-10, and adoption roadmap (#428)
* docs(architecture): add tool-neutral agent hub findings, ADR-10, and adoption roadmap
Comparative analysis of agentkit-forge sync engine vs Mystira.workspace
hand-authored .agents/ pattern. Documents 5-phase adoption roadmap to
converge both approaches: .agents/ as sync target, reflective guards,
.readme.yaml generation, cross-session traces, and schema formalisation.
Includes regenerated sync output (updated timestamps across all tools).
* docs(architecture): add competitive landscape and strategic research report
Comprehensive analysis of…
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
…438) * feat(config): add integrationBranch setting and PR base branch guard - Add `integrationBranch` field to overlay settings.yaml template (defaults to defaultBranch, allows dev/main distinction) - Add `overlays/retort/settings.yaml` — sets integrationBranch: dev for retort's own generated output - Add CLAUDE.md template section: Integration Branch header + PR Target Branch subsection with correct `gh pr create --base` example - Add synchronize.mjs mapping: `integrationBranch` var from overlay settings - Add hookify rule template: claude/rules/pr-base-branch.md warns when `gh pr create` is used without `--base {{integrationBranch}}` - Regenerate all sync outputs with Retort branding and integrationBranch This prevents the reverse-merge anti-pattern (PR targeting main instead of dev) that triggered PR #437. The rule is enforced at the framework level — every onboarded repo gets the guard baked into its CLAUDE.md and .claude/rules/pr-base-branch.md automatically. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(pr-review): address four Copilot review comments on PR #438 1. template-utils.mjs syncCmd: 'agentkit:sync' → 'retort:sync' in the generated GENERATED header's Regenerate instruction (line 680) 2. template-utils.mjs insertHeader: treat legacy 'GENERATED by AgentKit Forge' marker as "already present" to prevent double-headers during transition (line 721) 3. protect-templates.sh/.ps1: "is an Retort source file" → "is a Retort source file" (grammar fix, line 50) 4. review.md / project-review.md: "an Retort template" → "a Retort template" (grammar fix, line 239) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(docs): update ecosystem table with current repo names cockpit -> deck, ai-cadence -> phoenix-flow, ai-flume -> sluice. Add docket row (AI cost ops). Fix Name section reference. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * ci(runners): switch all workflows from self-hosted to ubuntu-latest Self-hosted runner is currently offline — all CI runs stuck in queue. Switching to GitHub-hosted ubuntu-latest to unblock PR merges while the custom runner is investigated. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Closes #397 - scripts/retort-sync.sh + .ps1: safety wrapper that previews changes (--dry-run), backs up overwritten files (--backup), verifies render target directories, and shows a post-sync git summary - docs/engineering/sync-safety.md: safe adoption workflow, file mode reference table, hook trigger explanation, and render target config - The pre-push-validate hook template issue (write-mode sync) is documented and tracked; a template fix is needed upstream Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
…fold noise - .gitattributes: add explicit eol=lf for all generated output dirs (.claude/, .cursor/, .clinerules/, .roo/, .windsurf/, .github/instructions/, .github/agents/, .github/chatmodes/, .github/prompts/) to prevent LF→CRLF conversion warnings on Windows after every retort:sync (#420) - .prettierignore: extend template exclusions to cover generated output directories so Prettier never reformats sync outputs or Handlebars YAML templates; also adds .agentkit/templates/**/*.hbs glob (#419) - docs/engineering/sync-file-modes.md: new reference document listing which files are scaffold-once vs managed vs always-overwrite, with manifest lookup instructions and workarounds for issues #417 (syncDate churn) and #418 (unresolved placeholder warnings missing file paths) (#421) Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
The block-agentkit-changes and branch-rules workflows only excepted JustAGhosT/retort. Since the canonical source repo is phoenixvc/retort, PRs from that org were incorrectly blocked from modifying .agentkit/ files. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…lder warnings Closes #417, #418 engine/synchronize.mjs: - {{syncDate}} now respects syncDateMode setting: 'run' (default) keeps current behaviour (today's date), 'version' emits the spec VERSION string, 'none' emits empty string — eliminating daily header churn engine/template-utils.mjs: - replacePlaceholders() accepts a 4th opts = {} param - Unresolved placeholder warnings now include the file path when opts.filePath is provided (e.g. "Warning: unresolved placeholders in .claude/rules/foo.md: {{missingVar}}") overlays/retort/settings.yaml: - syncDateMode: none — stops header churn in retort's own synced output spec/settings.yaml: - Documents sync.dateMode with all three options and per-repo override instructions Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Passing large strings (up to 3000 chars of truncated test/lint output) as jq --arg arguments hits the OS E2BIG limit on Windows Git Bash, crashing the stop and pre-push hooks with "Argument list too long". Fix: add emit_block() helper in stop-build-check.sh that pipes the reason string via stdin using printf '%s' | jq -Rs, avoiding argv entirely. Apply the same stdin pattern to pre-push-validate.sh. Fixes #453. Applied to both generated hooks and template sources. Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(engine): skip shebang line in legacy-header stripping to prevent recursion
insertHeader's AgentKit Forge → Retort migration path stripped leading comment
lines by advancing index i while lines[i] matched a comment prefix. Shebang
lines (#!) start with '#!' not '# ', so i stayed at 0, bodyWithoutLegacyHeader
equalled the original content, and the recursive call hit the same branch again
→ RangeError: Maximum call stack size exceeded.
Fix: detect and preserve the shebang line before the comment-stripping loop,
then restore it when rebuilding strippedContent. Also skip the claude-review
CI job when CLAUDE_CODE_OAUTH_TOKEN secret is not configured to avoid spurious
401 failures on forks and repos where the secret has not been set.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(engine): wrap tmpDir cleanup to prevent ENOTEMPTY masking primary error
fs.rm() defaults to maxRetries:0, so a single ENOTEMPTY from rmdir
(common on tmpfs/overlayfs when a prior error left files in the temp
directory) would throw and mask the original sync error. Two changes:
1. Add maxRetries:3 / retryDelay:100 so transient ENOTEMPTY is retried
instead of immediately aborting cleanup.
2. Wrap the entire cleanup in try/catch so any remaining cleanup failure
is logged at DEBUG level rather than propagating and hiding the real
error that caused the sync to fail.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(engine): guard legacy-header check to file start to prevent recursion
content.includes('GENERATED by AgentKit Forge') triggered on any file
containing the string — including rules/language-instruction docs that
reference it in their body text (e.g. template-protection.md rendered
from rules.yaml). After stripping the header lines the body still
contained the string, causing infinite recursion.
Fix: add startsWithLegacyHeader() helper that skips an optional shebang
and blank lines before checking whether the FIRST substantive line is
the legacy header. Only then is the migration path taken.
Also run prettier on all four engine files to clear the pre-existing
formatting check failure.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(ci): use env-based step guard for claude-review token check
The job-level 'if: \${{ secrets.X != \"\" }}' guard is not reliably
supported across all GitHub Actions runner versions and can produce
'Unrecognized named-value: secrets' parse errors that break the entire
workflow. Move the guard to the step level using an env var (env context
IS supported in step-level if conditions).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore(sync): regenerate outputs after insertHeader legacy-header migration fix
Runs the full sync pass to migrate all generated files from
"GENERATED by AgentKit Forge" headers to "GENERATED by Retort" headers,
following the fix to the insertHeader infinite-recursion bug.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(sync): resolve unresolved three-way merge conflict markers in managed files
Strips stale conflict markers from 18 managed files (scripts/*.sh,
AGENT_TEAMS.md, docs/history/*/README.md) left from the agentkit-forge
→ retort header migration. The validate-templates drift check runs sync
without a scaffold-cache, so these conflict-marker lines appeared as
uncommitted deletions.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* test(engine): update assertions from agentkit:sync prefix to retort:sync
Three tests had hardcoded log prefix strings from before the CLI rename.
Updated to match the current [retort:sync] output prefix.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(engine): update getGeneratedHeader to emit retort:sync in Regenerate line
The function was still generating 'agentkit:sync' after the CLI rename.
Both 'retort:sync' and 'agentkit:sync' are valid aliases in package.json,
but headers should show the preferred new name.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore(sync): regenerate outputs — update Regenerate line from agentkit:sync to retort:sync
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(sync): remove residual conflict markers from managed files (round 2)
The chore(sync) regenerate commit (82d455c) re-introduced conflict markers
into AGENT_TEAMS.md and docs/history/*/README.md by running sync without
a scaffold-cache, which overwrote the clean versions from 3ebbec7 with
the template output that still had unresolved merge markers.
Restored all 7 files from the clean state at 3ebbec7.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore(deps): remove package-lock.json in favour of pnpm
packageManager is already set to pnpm@10.30.3 and pnpm-lock.yaml is
the canonical lockfile — the npm lockfile was stale and redundant.
Also updates vscode theme name to match current VS Code display name.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(ci): fix prettier check — format files and extend .prettierignore
Format 69 files that were failing the prettier CI check (pre-existing).
Extend .prettierignore to cover:
- .claude/state/** — runtime state files
- .agentkit/state/** — runtime state files
- .agentkit/overlays/** — protected source-of-truth YAML
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
…e, /start TUI features
…start flags, CI badge
…ENOTEMPTY race Fixes intermittent ENOTEMPTY failures in CI when rmSync fires before the OS flushes directory handles from async writes.
…tform-syncer.mjs Removes 1,287 lines of private sync function copies from synchronize.mjs, delegating to platform-syncer.mjs. Also adds syncJunie (JetBrains AI) and fixes templateMetaMap/syncClaudeAgents divergences.
…sks/ Adds TasksPanel TUI component that reads active task JSON files and renders them grouped by status (working, input-required, accepted, submitted). Wired into App.jsx alongside MCPPanel and StatusBar.
Handlebars {{#if}} blocks in .agentkit/templates/**/*.json are invalid
JSON and cause prettier's parser to error. Extend the existing template
ignore pattern (added in #419) to cover *.json files.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds missing write-side git commands and shell utilities to the permissions spec so agents can run without manual approval prompts. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(start): migrate src/start to TypeScript (#502) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * style(start): fix prettier formatting in CommandPalette.tsx * chore: re-sync after permissions spec update Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * style: fix prettier on generated SKILL.md files * chore: re-sync generated outputs * fix(sync): fix template trailing whitespace and re-sync with retort overlay Two root causes for the Validate/drift CI failure: 1. The SKILL.md templates had ` {{/if}}` (leading spaces before the closing tag) which produced a trailing-whitespace line on Linux. Fixed by removing the leading spaces. 2. The worktree basename is feat-ts-migration-start, not retort, so the sync engine fell back to __TEMPLATE__ overlay (dateMode: run) instead of the retort overlay (syncDateMode: none). All generated files gained a last_updated date that CI's sync (checked out to …/retort/retort) would clear to ''. Re-ran sync with --overlay retort to produce the stable empty date that CI expects. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * style: fix prettier on sync-generated outputs Post-sync Prettier auto-format for files that the sync engine produced with table formatting or whitespace that Prettier doesn't accept on Linux. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
…ml (#504) * feat(mcp): make browser/crawler MCP servers conditional on project.yaml Adds buildBrowserTestingVars() to var-builders.mjs which derives usesPlaywright and usesBrowser boolean flags from testing.e2e in project.yaml. Wires them into synchronize.mjs alongside existing heuristic vars. Updates templates/mcp/servers.json to conditionally include the playwright MCP server (when usesPlaywright), puppeteer (when usesBrowser with non-playwright tools), and storybook-crawler (when hasStorybook) — omitting all three when unused. Closes #503 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(mcp): correct storybook MCP package to @storybook/mcp * chore: regenerate after sync (fix CI drift) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * chore: re-sync generated outputs Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * chore: rebase onto dev + re-sync (--overlay retort) * fix: run prettier on CI-flagged files --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore: rebase onto dev + re-sync * feat(junie): add JetBrains Junie as a sync target Add `junie` to renderTargets in the retort overlay settings. Retort now generates `.junie/guidelines.md` with project-level agent instructions for JetBrains AI (Rider, IntelliJ, etc). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
…nores - Add @vitest/coverage-v8 to .agentkit devDependencies - Add json-summary reporter and 80% line/branch/function thresholds to vitest.config.mjs - Add `coverage` script to .agentkit/package.json - Extend .prettierignore to cover .claude/skills/** and .agents/skills/** sync outputs Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
Mention Blocks like a regular teammate with your question or request: @blocks review this pull request Run |
Contributor
|
Important Review skippedAuto reviews are disabled on base/target branches other than the default branch. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
…, retort-plugins - Add coverage badge (CI now enforces 80% with v8) - Mark JetBrains Junie as shipped (feat #506 merged) - Update /start TUI description and repo layout to reflect TypeScript migration - Add retort-plugins to ecosystem table Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…lls/ Move skills/repo-naming/SKILL.md → .agents/skills/repo-naming/SKILL.md (correct distribution location for the sync engine) and register it in .agentkit/spec/skills.yaml under a new PROJECT UTILITIES section. scope: global, source: retort — sync will not overwrite this hand-authored skill since it has no corresponding command template. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The main branch had one unmerged commit (184a8e9 feat(sync): metrics aggregation, worktree isolation, sync-report, and scaffold policy enhancements) that diverged from dev. Resolved 83 conflicts by taking dev's versions (which include newer spec and sync outputs), and keeping dev's intentional deletions of agents.yaml and grant-hunter.md. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Retort Source Change DetectedThis PR modifies files in the Retort source directories:
These are the upstream source-of-truth for all generated AI tool configs. Review checklist
|
… item - Switch `pnpm test` → `pnpm coverage` so CI collects v8 coverage - Add Coverage summary step that reads coverage-summary.json and writes lines/branches/functions percentages to the workflow step summary - Mark AGENT_BACKLOG P0 test-framework item as Done Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…an and investability map v2
- Add @vitest/coverage-v8 to .agentkit/pnpm-lock.yaml (standalone lockfile used by fresh-install tests and CI; root workspace lockfile was already updated but the standalone one was missed) - Run prettier on .cursor/commands/brand.md, expand.md, and handoff docs that were failing the prettier check in CI Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…in SKILL.md
Handlebars inline block tags ({{#if}} and {{/if}} on lines with leading
spaces) emit the whitespace even when the block is falsy, producing ` `
phantom lines and mis-indented list items. Moving the tags to column 0
makes them standalone — Handlebars strips the entire line when the block
is empty.
Affected: claude and codex SKILL.md templates, and all generated skill
output files.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
@vitest/coverage-v8to.agentkit/devDependenciesjson-summaryreporter and 80% line/branch/function thresholds tovitest.config.mjscoveragescript to.agentkit/package.json.prettierignoreto cover.claude/skills/**and.agents/skills/**sync outputsCloses the P0
task-p0-test-frameworkbacklog item.Test plan
cd .agentkit && npx vitest run— 1486 passed, 1 skipped, 0 failurescd .agentkit && npx vitest run --coverage— generatescoverage/coverage-summary.json🤖 Generated with Claude Code