Adding /bad (BMAD Autonomous Development)#3
Adding /bad (BMAD Autonomous Development)#3stephenleo wants to merge 4 commits intobmad-code-org:mainfrom
Conversation
WalkthroughAdded a new declarative community registry entry Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ 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 |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@registry/community/bmad-autonomous-development.yaml`:
- Around line 24-28: The metadata is inconsistent: the YAML contains
approved_tag/approved_sha/approved_date while reviewer is still "pending";
either remove the approval fields (approved_tag, approved_sha, approved_date)
until a real reviewer completes the review, or replace reviewer: pending with
the actual GitHub handle of the approver so the approval fields are
accurate—update the keys approved_tag, approved_sha, approved_date or reviewer
accordingly to restore consistency.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 5cab1d72-798c-4df6-b4e3-32e01c06af69
📒 Files selected for processing (1)
registry/community/bmad-autonomous-development.yaml
| version: "1.0.0" | ||
| approved_tag: v1.0.0 | ||
| approved_sha: a4833dd1773d8c7979d5ec66733fec879e26c3c6 | ||
| approved_date: "2026-04-05" | ||
| reviewer: pending |
There was a problem hiding this comment.
Approval metadata is inconsistent (approved_* set but reviewer is placeholder).
Line 28 should be a real GitHub handle if Lines 25–27 represent a completed approval. Otherwise, defer approved_tag/approved_sha/approved_date until approval is finalized.
Suggested metadata correction pattern
version: "1.0.0"
-approved_tag: v1.0.0
-approved_sha: a4833dd1773d8c7979d5ec66733fec879e26c3c6
-approved_date: "2026-04-05"
-reviewer: pending
+approved_tag: v1.0.0
+approved_sha: a4833dd1773d8c7979d5ec66733fec879e26c3c6
+approved_date: "2026-04-05"
+reviewer: <github-handle>
trust_tier: unverifiedIf review is not complete yet, keep reviewer: pending and remove approval fields until merge-time approval.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@registry/community/bmad-autonomous-development.yaml` around lines 24 - 28,
The metadata is inconsistent: the YAML contains
approved_tag/approved_sha/approved_date while reviewer is still "pending";
either remove the approval fields (approved_tag, approved_sha, approved_date)
until a real reviewer completes the review, or replace reviewer: pending with
the actual GitHub handle of the approver so the approval fields are
accurate—update the keys approved_tag, approved_sha, approved_date or reviewer
accordingly to restore consistency.
update to v1.1.0
|
bumped to v1.1.0 |
|
bumped to v1.2.0 |
1 participant
New Module Submission
Module name: BMAD Autonomous Development (BAD)
Repository: https://github.com/stephenleo/bmad-autonomous-development
Version tag: v1.0.0
Commit SHA: a4833dd1773d8c7979d5ec66733fec879e26c3c6
Category / Subcategory: software-development/dev-tools
Checklist
.claude-plugin/marketplace.jsonSKILL.mdValidate Module (VM)with no critical findingsREADME.mddocuments what the module does, how to install, and any external dependenciesLICENSEfile present in source reporegistry/community/with pinned tag, SHA, category, and subcategorycategories.yamlDescription
TLDR: 🤖 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.
Details:
As a heavy BMAD user, I noticed that I spend most of my time in Brainstorm, PRD and Architecture. Once the Epics and stories are written, I mostly handoff implementation to the Agents which run autonomously. /bad writes up the autonomous execution as a re-usable skill.
BAD automates your entire sprint execution. A lightweight coordinator orchestrates the pipeline — it never writes code itself. Every unit of work is delegated to a dedicated subagent with a fresh context window, keeping each agent fully focused on its single task.
Once your epics and stories are planned, BAD takes over:
MODEL_STANDARDsubagent) Builds a dependency graph from your sprint backlog — maps story dependencies, syncs GitHub PR status, and identifies what's ready to work onMAX_PARALLEL_STORIESstories simultaneously — each in its own isolated git worktree — each through a sequential 7-step pipeline:MODEL_STANDARDsubagent) —bmad-create-story: generates and validates the story specMODEL_STANDARDsubagent) —bmad-testarch-atdd: generates failing acceptance testsMODEL_STANDARDsubagent) —bmad-dev-story: implements the codeMODEL_STANDARDsubagent) —bmad-testarch-test-review: reviews test quality, applies fixesMODEL_QUALITYsubagent) —bmad-code-review: reviews and fixes the implementationMODEL_STANDARDsubagent) — commit, push, open PR, monitor CI, fix any failing checksMODEL_STANDARDsubagent) — PR code review: reviews diff, applies fixes, pushes cleanMODEL_STANDARDsubagent) Optionally auto-merges batch PRs sequentially (lowest story number first), resolving any conflictsWith BAD, AI agents build my entire sprint while I sleep! I get to focus on what's most fulfilling to me: the brainstorming and PRD phases. Used it successfully to build CShip (https://github.com/stephenleo/cship) and other projects.
External Dependencies
None. Only Depends on BMAD method
Summary by CodeRabbit