bc950dec99
Agents marked stories 'done' but left ALL tasks unchecked, Dev Agent Records empty,
and implemented different code than story specifications. This happened because
workflows had NO ENFORCEMENT - everything was optional theater.
**Enforcement Added (7 files changed):**
1. **workflow.xml** - Filename validation at completion
- Verifies output matches canonical format
- Auto-renames wrong-named files
- Prevents 'story-' prefix proliferation
2. **step-04-implement.md** - Per-task checkbox enforcement
- After EVERY task: Verify checkbox updated
- Auto-fix with Edit tool if missing
- 3-attempt retry before halt
- Batch tasks: Loop through all, verify each
3. **step-10-complete.md** - Final verification before commit
- Count checked tasks (HALT if zero)
- Verify Dev Agent Record filled (HALT if empty)
- Auto-fix from git commit if missing
4. **batch-super-dev Step 4.5** - Mandatory reconciliation
- Verify checked_tasks > 0 after reconciliation
- Auto-fix: Read commit → match tasks → check boxes
- Fill Dev Agent Record from commit message
- Override status to 'in-progress' if <80% complete
5. **super-dev-pipeline/workflow.yaml** - Canonical filename pattern
- Changed: story-*.md → *.md (removed 'story-' prefix)
6. **multi-agent-review/workflow.yaml** - Canonical format
- Changed: story-{story_id}.md → {story_id}.md
7. **batch-super-dev instructions** - ONE canonical format
- Format: {epic}-{story}-{slug}.md (NO 'story-' prefix)
- Auto-rename legacy 'story-' files
- Removed all 6 pattern variations
- Single format everywhere
**Behavioral Changes:**
- Before: Agents could skip tasks, leave checkboxes unchecked, claim 'done'
- After: Auto-fix with retry, HALT only if all attempts exhausted
- Before: Multiple filename formats caused confusion
- After: ONE format, auto-rename legacy files
- Before: No verification, trust agent claims
- After: Verify EVERYTHING, auto-fix failures
**Tested in production:**
- Epic 18 batch execution revealed all failure modes
- Every enforcement added addresses real observed failure
- No theoretical fixes - all battle-tested
**Quality Standards:**
Lives are at stake. Zero tolerance for unchecked tasks or missing documentation.
Ref: craftedcall commits 9e299817e, e607a4422, 6a9d87176, 0240b4742, 91f73c7f4
|
||
|---|---|---|
| .claude-commands | ||
| .github | ||
| .husky | ||
| .vscode | ||
| docs | ||
| resources/skills | ||
| scripts | ||
| src | ||
| test | ||
| tools | ||
| website | ||
| .coderabbit.yaml | ||
| .gitignore | ||
| .markdownlint-cli2.yaml | ||
| .npmignore | ||
| .npmrc | ||
| .nvmrc | ||
| .prettierignore | ||
| ASSESSMENT_SUMMARY.txt | ||
| BMAD-WORKFLOW-IMPROVEMENTS.md | ||
| CHANGELOG.md | ||
| CNAME | ||
| CONTRIBUTING.md | ||
| CONTRIBUTORS.md | ||
| FEATURE-SUMMARY-v1.5.0.md | ||
| FEATURE-SUMMARY.md | ||
| GSDMAD-ARCHITECTURE.md | ||
| INTEGRATION-NOTES.md | ||
| LICENSE | ||
| PR-DESCRIPTION.md | ||
| PR-STORY-PIPELINE.md | ||
| README-changes.md | ||
| README.md | ||
| SECURITY.md | ||
| TESTING-GUIDE.md | ||
| TRADEMARK.md | ||
| Wordmark.png | ||
| banner-bmad-method.png | ||
| eslint.config.mjs | ||
| package-lock.json | ||
| package.json | ||
| prettier.config.mjs | ||
| vitest.config.js | ||
README.md
Breakthrough Method of Agile AI Driven Development — An AI-driven agile development framework with 21 specialized agents, 50+ guided workflows, and scale-adaptive intelligence that adjusts from bug fixes to enterprise systems.
100% free and open source. No paywalls. No gated content. No gated Discord. We believe in empowering everyone, not just those who can pay.
Why BMad?
Traditional AI tools do the thinking for you, producing average results. BMad agents act as expert collaborators who guide you through structured workflows to bring out your best thinking.
- Scale-Adaptive: Automatically adjusts planning depth based on project complexity (Level 0-4)
- Structured Workflows: Grounded in agile best practices across analysis, planning, architecture, and implementation
- Specialized Agents: 12+ domain experts (PM, Architect, Developer, UX, Scrum Master, and more)
- Party Mode: Bring multiple agent personas into one session to plan, troubleshoot, or discuss your project collaboratively
- Complete Lifecycle: From brainstorming to deployment, with just-in-time documentation
Quick Start
Prerequisites: Node.js v20+
npx bmad-method@alpha install
Follow the installer prompts, then open your AI IDE (Claude Code, Cursor, Windsurf, etc.) in the project folder.
Not sure what to do? Run
/bmad-help— it tells you exactly what's next and what's optional. You can also ask it questions like/bmad-help How should I build a web app for XYZ?
The workflows below show the fastest path to working code. You can also load agents directly for a more structured process, extensive planning, or to learn about agile development practices — the agents guide you with menus, explanations, and elicitation at each step.
Simple Path (Quick Flow)
Bug fixes, small features, clear scope — 3 commands:
/quick-spec— analyzes your codebase and produces a tech-spec with stories/dev-story— implements each story/code-review— validates quality
Full Planning Path (BMad Method)
Products, platforms, complex features — structured planning then build:
/product-brief— define problem, users, and MVP scope/create-prd— full requirements with personas, metrics, and risks/create-architecture— technical decisions and system design/create-epics-and-stories— break work into prioritized stories/sprint-planning— initialize sprint tracking- Repeat per story:
/create-story→/dev-story→/code-review
Every step tells you what's next. Optional phases (brainstorming, research, UX design) are available when you need them — ask /bmad-help anytime. For a detailed walkthrough, see the Getting Started Tutorial.
Modules
BMad Method extends with official modules for specialized domains. Modules are available during installation and can be added to your project at any time.
| Module | GitHub | NPM | Purpose |
|---|---|---|---|
| BMad Method (BMM) | bmad-code-org/BMAD-METHOD | bmad-method | Core framework with 34+ workflows across 4 development phases |
| BMad Builder (BMB) | bmad-code-org/bmad-builder | bmad-builder | Create custom BMad agents, workflows, and domain-specific modules |
| Game Dev Studio (BMGD) | bmad-code-org/bmad-module-game-dev-studio | bmad-game-dev-studio | Game development workflows for Unity, Unreal, and Godot |
| Creative Intelligence Suite (CIS) | bmad-code-org/bmad-module-creative-intelligence-suite | bmad-creative-intelligence-suite | Innovation, brainstorming, design thinking, and problem-solving |
Documentation
Full Documentation — Tutorials, how-to guides, concepts, and reference
For v4 Users
Community
- Discord — Get help, share ideas, collaborate
- YouTube — Tutorials, master class, and podcast (launching Feb 2025)
- GitHub Issues — Bug reports and feature requests
- Discussions — Community conversations
Support BMad
BMad is free for everyone — and always will be. If you'd like to support development:
- ⭐ Star us on GitHub — Helps others discover BMad
- 📺 Subscribe on YouTube — Master class launching Feb 2026
- ☕ Buy Me a Coffee — Fuel the development
- 🏢 Corporate sponsorship — DM on Discord
- 🎤 Speaking & Media — Available for conferences, podcasts, interviews (Discord)
Contributing
We welcome contributions! See CONTRIBUTING.md for guidelines.
License
MIT License — see LICENSE for details.
BMad and BMAD-METHOD are trademarks of BMad Code, LLC. See TRADEMARK.md for details.
See CONTRIBUTORS.md for contributor information.