Merge pull request #4 from stephenleo/bad-v1.2.0-audit

feat(bad): v1.2.0 — watchdog integration, 7-step pipeline, consistency audit

Author: stephenleo

.claude-plugin/marketplace.json

@@ -24,7 +24,7 @@
       "name": "bmad-bad",
       "source": "./",
       "description": "Autonomous development orchestrator for the BMad Method. Runs fully autonomous parallel multi-agent pipelines through the full story lifecycle (create → dev → review → PR) driven by your sprint backlog and dependency graph.",
-      "version": "1.1.0",
+      "version": "1.2.0",
       "author": { "name": "Marie Stephen Leo" },
       "skills": [
         "./skills/bad"

README.md

@@ -12,12 +12,14 @@ Once your epics and stories are planned, BAD takes over:
 
 1. *(`MODEL_STANDARD` subagent)* Builds a dependency graph from your sprint backlog — maps story dependencies, syncs GitHub PR status, and identifies what's ready to work on
 2. Picks ready stories from the graph, respecting epic ordering and dependencies
-3. Runs up to `MAX_PARALLEL_STORIES` stories simultaneously — each in its own isolated git worktree — each through a sequential 5-step pipeline:
+3. Runs up to `MAX_PARALLEL_STORIES` stories simultaneously — each in its own isolated git worktree — each through a sequential 7-step pipeline:
    - **Step 1** *(`MODEL_STANDARD` subagent)* — `bmad-create-story`: generates and validates the story spec
-   - **Step 2** *(`MODEL_STANDARD` subagent)* — `bmad-dev-story`: implements the code
-   - **Step 3** *(`MODEL_QUALITY` subagent)* — `bmad-code-review`: reviews and fixes the implementation
-   - **Step 4** *(`MODEL_STANDARD` subagent)* — commit, push, open PR, monitor CI, fix any failing checks
-   - **Step 5** *(`MODEL_STANDARD` subagent)* — PR code review: reviews diff, applies fixes, pushes clean
+   - **Step 2** *(`MODEL_STANDARD` subagent)* — `bmad-testarch-atdd`: generates failing acceptance tests
+   - **Step 3** *(`MODEL_STANDARD` subagent)* — `bmad-dev-story`: implements the code
+   - **Step 4** *(`MODEL_STANDARD` subagent)* — `bmad-testarch-test-review`: reviews test quality, applies fixes
+   - **Step 5** *(`MODEL_QUALITY` subagent)* — `bmad-code-review`: reviews and fixes the implementation
+   - **Step 6** *(`MODEL_STANDARD` subagent)* — commit, push, open PR, monitor CI, fix any failing checks
+   - **Step 7** *(`MODEL_STANDARD` subagent)* — PR code review: reviews diff, applies fixes, pushes clean
 4. *(`MODEL_STANDARD` subagent)* Optionally auto-merges batch PRs sequentially (lowest story number first), resolving any conflicts
 5. Waits, then loops back for the next batch — until the entire sprint is done
 
@@ -91,6 +93,7 @@ BAD is configured at install time (`/bad setup`) and stores settings in the `bad
 | `WAIT_TIMER_SECONDS` | `3600` | Wait between batches |
 | `RETRO_TIMER_SECONDS` | `600` | Delay before auto-retrospective |
 | `CONTEXT_COMPACTION_THRESHOLD` | `80` | Context window % at which to compact context |
+| `STALE_TIMEOUT_MINUTES` | `60` | Minutes of subagent inactivity before watchdog alerts (0 = disabled) |
 | `TIMER_SUPPORT` | `true` | Use native platform timers; `false` for prompt-based continuation |
 | `MONITOR_SUPPORT` | `true` | Use the Monitor tool for CI/PR-merge polling; `false` for Bedrock/Vertex/Foundry |
 | `API_FIVE_HOUR_THRESHOLD` | `80` | (Claude Code) 5-hour usage % at which to pause |

docs/index.md

@@ -68,36 +68,40 @@ Run with optional runtime overrides:
 Once your epics and stories are planned, BAD takes over:
 
 1. *(`MODEL_STANDARD` subagent)* Builds a dependency graph from your sprint backlog — maps story dependencies, syncs GitHub PR status, and identifies what's ready to work on
-2. Picks ready stories from the graph, respecting epic ordering and dependencies
-3. Runs up to `MAX_PARALLEL_STORIES` stories simultaneously — each in its own isolated git worktree — each through a sequential 5-step pipeline. **Every step runs in a dedicated subagent with a fresh context window**, keeping the coordinator lean and each agent fully focused on its single task:
+2. Picks ready stories from the graph, respecting epic ordering and dependencies; runs a blocking epic-level test design step (`bmad-testarch-test-design`) once when starting each new epic
+3. Runs up to `MAX_PARALLEL_STORIES` stories simultaneously — each in its own isolated git worktree — each through a sequential 7-step pipeline. **Every step runs in a dedicated subagent with a fresh context window**, keeping the coordinator lean and each agent fully focused on its single task:
    - **Step 1** *(`MODEL_STANDARD` subagent)* — `bmad-create-story`: generates and validates the story spec
-   - **Step 2** *(`MODEL_STANDARD` subagent)* — `bmad-dev-story`: implements the code
-   - **Step 3** *(`MODEL_QUALITY` subagent)* — `bmad-code-review`: reviews and fixes the implementation
-   - **Step 4** *(`MODEL_STANDARD` subagent)* — commit, push, open PR, monitor CI, fix any failing checks
-   - **Step 5** *(`MODEL_STANDARD` subagent)* — PR code review: reviews diff, applies fixes, pushes clean
+   - **Step 2** *(`MODEL_STANDARD` subagent)* — `bmad-testarch-atdd`: generates failing acceptance tests
+   - **Step 3** *(`MODEL_STANDARD` subagent)* — `bmad-dev-story`: implements the code
+   - **Step 4** *(`MODEL_STANDARD` subagent)* — `bmad-testarch-test-review`: reviews test quality, applies fixes
+   - **Step 5** *(`MODEL_QUALITY` subagent)* — `bmad-code-review`: reviews and fixes the implementation
+   - **Step 6** *(`MODEL_STANDARD` subagent)* — commit, push, open PR, monitor CI, fix any failing checks
+   - **Step 7** *(`MODEL_STANDARD` subagent)* — PR code review: reviews diff, applies fixes, pushes clean
 4. *(`MODEL_STANDARD` subagent)* Optionally auto-merges batch PRs sequentially (lowest story number first), resolving any conflicts
-5. Waits, then loops back for the next batch — until the entire sprint is done
+5. On epic completion, optionally runs a retrospective (`bmad-retrospective`) after a `RETRO_TIMER_SECONDS` countdown — the user can trigger it early, skip it, or stop BAD
+6. Waits, then loops back for the next batch — until the entire sprint is done
 
 ## Configuration
 
 BAD is configured at install time (`/bad setup`) and stores settings in the `bad:` section of `_bmad/config.yaml`. All values can be overridden at runtime with `KEY=VALUE` args.
 
-| Variable | Config Key | Default | Description |
-|---|---|---|---|
-| `MAX_PARALLEL_STORIES` | `max_parallel_stories` | `3` | Stories to run per batch |
-| `WORKTREE_BASE_PATH` | `worktree_base_path` | `.worktrees` | Base directory for per-story git worktrees (relative to repo root) |
-| `MODEL_STANDARD` | `model_standard` | `sonnet` | Model for create, dev, and PR steps |
-| `MODEL_QUALITY` | `model_quality` | `opus` | Model for code review step |
-| `AUTO_PR_MERGE` | `auto_pr_merge` | `false` | Auto-merge PRs sequentially after each batch |
-| `RUN_CI_LOCALLY` | `run_ci_locally` | `false` | Run CI locally instead of GitHub Actions |
-| `WAIT_TIMER_SECONDS` | `wait_timer_seconds` | `3600` | Seconds to wait between batches |
-| `RETRO_TIMER_SECONDS` | `retro_timer_seconds` | `600` | Seconds before auto-retrospective after epic completion |
-| `CONTEXT_COMPACTION_THRESHOLD` | `context_compaction_threshold` | `80` | Context window % at which to compact context |
-| `TIMER_SUPPORT` | `timer_support` | `true` | Use native platform timers; `false` for prompt-based continuation |
-| `MONITOR_SUPPORT` | `monitor_support` | `true` | Use the Monitor tool for CI/PR-merge polling; `false` for Bedrock/Vertex/Foundry |
-| `API_FIVE_HOUR_THRESHOLD` | `api_five_hour_threshold` | `80` | (Claude Code) 5-hour usage % at which to pause |
-| `API_SEVEN_DAY_THRESHOLD` | `api_seven_day_threshold` | `95` | (Claude Code) 7-day usage % at which to pause |
-| `API_USAGE_THRESHOLD` | `api_usage_threshold` | `80` | (Other harnesses) Generic usage % at which to pause |
+| Variable | Default | Description |
+|---|---|---|
+| `MAX_PARALLEL_STORIES` | `3` | Stories to run per batch |
+| `WORKTREE_BASE_PATH` | `.worktrees` | Base directory for per-story git worktrees (relative to repo root) |
+| `MODEL_STANDARD` | `sonnet` | Model for create, ATDD, dev, test review, and PR steps |
+| `MODEL_QUALITY` | `opus` | Model for code review step |
+| `AUTO_PR_MERGE` | `false` | Auto-merge PRs sequentially after each batch |
+| `RUN_CI_LOCALLY` | `false` | Run CI locally instead of GitHub Actions |
+| `WAIT_TIMER_SECONDS` | `3600` | Seconds to wait between batches |
+| `RETRO_TIMER_SECONDS` | `600` | Seconds before auto-retrospective after epic completion |
+| `CONTEXT_COMPACTION_THRESHOLD` | `80` | Context window % at which to compact context |
+| `STALE_TIMEOUT_MINUTES` | `60` | Minutes of subagent inactivity before watchdog alerts (0 = disabled) |
+| `TIMER_SUPPORT` | `true` | Use native platform timers; `false` for prompt-based continuation |
+| `MONITOR_SUPPORT` | `true` | Use the Monitor tool for CI/PR-merge polling; `false` for Bedrock/Vertex/Foundry |
+| `API_FIVE_HOUR_THRESHOLD` | `80` | (Claude Code) 5-hour usage % at which to pause |
+| `API_SEVEN_DAY_THRESHOLD` | `95` | (Claude Code) 7-day usage % at which to pause |
+| `API_USAGE_THRESHOLD` | `80` | (Other harnesses) Generic usage % at which to pause |
 
 ## Agent Harness Support