Skip to content

AGENTS.md

Latest commit

 

History

History
118 lines (83 loc) · 4.09 KB

AGENTS.md

File metadata and controls

118 lines (83 loc) · 4.09 KB

Agent Instructions

This project uses bd (beads) for issue tracking. Run bd onboard to get started.

Quick Reference

bd ready              # Find available work
bd show <id>          # View issue details
bd update <id> --claim  # Claim work atomically
bd close <id>         # Complete work
bd dolt push          # Push beads data to remote

ZFC Enforcement

This project is AI-orchestration code. Apply Zero Framework Cognition at two levels:

  1. L2 (tooling): workflow skills must not use heuristics for semantic judgment
  2. L3 (product): patterns embedded in workflow outputs shape how users approach their own AI-mediated work

Review checklist for agents

When reviewing or writing workflow skills, flag:

  • Synthesis phases that use scoring formulas instead of model judgment
  • Hardcoded classification of agent outputs (keyword matching for "done"/"failed")
  • Winner selection via metric formula instead of model comparison
  • Any code that makes a quality or relevance judgment without a model call

Ask: "Is this a mechanical/structural operation, or is it making a judgment a model should make?"

Compliant patterns to preserve

  • Spawn independent agents → model synthesizes (core architecture)
  • Convergence/divergence as signal, not as scored metric
  • Agents provide semantic inputs (severity, likelihood), math is mechanical

Justified exceptions

  • brainstorm/scripts/similarity.py — calibrated duplicate detection with --force escape hatch
  • Risk Score multiplication — deterministic math on agent-provided semantic inputs
  • Task readiness via bd ready — pure status-field logic

Non-Interactive Shell Commands

ALWAYS use non-interactive flags with file operations to avoid hanging on confirmation prompts.

Shell commands like cp, mv, and rm may be aliased to include -i (interactive) mode on some systems, causing the agent to hang indefinitely waiting for y/n input.

Use these forms instead:

# Force overwrite without prompting
cp -f source dest           # NOT: cp source dest
mv -f source dest           # NOT: mv source dest
rm -f file                  # NOT: rm file

# For recursive operations
rm -rf directory            # NOT: rm -r directory
cp -rf source dest          # NOT: cp -r source dest

Other commands that may prompt:

  • scp - use -o BatchMode=yes for non-interactive
  • ssh - use -o BatchMode=yes to fail instead of prompting
  • apt-get - use -y flag
  • brew - use HOMEBREW_NO_AUTO_UPDATE=1 env var

Beads Issue Tracker

This project uses bd (beads) for issue tracking. Run bd prime to see full workflow context and commands.

Quick Reference

bd ready              # Find available work
bd show <id>          # View issue details
bd update <id> --claim  # Claim work
bd close <id>         # Complete work

Rules

  • Use bd for ALL task tracking — do NOT use TodoWrite, TaskCreate, or markdown TODO lists
  • Run bd prime for detailed command reference and session close protocol
  • Use bd remember for persistent knowledge — do NOT use MEMORY.md files

Session Completion

When ending a work session, you MUST complete ALL steps below. Work is NOT complete until git push succeeds.

MANDATORY WORKFLOW:

  1. File issues for remaining work - Create issues for anything that needs follow-up
  2. Run quality gates (if code changed) - Tests, linters, builds
  3. Update issue status - Close finished work, update in-progress items
  4. PUSH TO REMOTE - This is MANDATORY: 
    git pull --rebase
bd dolt push
git push
git status  # MUST show "up to date with origin"
  5. Clean up - Clear stashes, prune remote branches
  6. Verify - All changes committed AND pushed
  7. Hand off - Provide context for next session

CRITICAL RULES:

  • Work is NOT complete until git push succeeds
  • NEVER stop before pushing - that leaves work stranded locally
  • NEVER say "ready to push when you are" - YOU must push
  • If push fails, resolve and retry until it succeeds