BMAD-WORKFLOW
**BMAD (Business-Minded Agile Development)** - AI-driven agile development automation with role-based agents
Lightweight alternative to BMAD for rapid prototyping and simple feature development
> /plugin marketplace add cexll/myclaudeHow it fires
How this agent gets triggered: by you, by Claude, or both.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Lightweight alternative to BMAD for rapid prototyping and simple feature development
> Lightweight alternative to BMAD for rapid prototyping and simple feature development
A streamlined 4-phase workflow that focuses on getting from requirements to working code quickly:
**Requirements → Implementation → Review → Testing**
Perfect for:
/requirements-pilot "Implement JWT authentication with refresh tokens" # Automated workflow: # 1. Requirements generation (90% quality gate) # 2. Code implementation # 3. Code review # 4. Testing strategy
**Use Requirements Workflow** when:
**Use BMAD Workflow** when:
**Quality Criteria (100 points)**:
1. Read requirements + repository context 2. Implement features following requirements 3. Create or modify code files 4. Follow existing code conventions
**Review Status**:
1. Create test strategy from requirements 2. Generate test cases 3. Execute tests (unit, integration) 4. Report results
Generated in `.claude/requirements/{feature-name}/`:
.claude/requirements/jwt-authentication/ ├── 01-requirements.md # Functional requirements (score ≥ 90) ├── 02-implementation.md # Implementation summary ├── 03-review.md # Code review report └── 04-testing.md # Test strategy and results
# Standard workflow /requirements-pilot "Add API rate limiting" # With specific technology /requirements-pilot "Redis caching layer with TTL management" # Bug fix with requirements /requirements-pilot "Fix login session timeout issue"
| Category | Points | Description | |----------|--------|-------------| | Clarity | 30 | Unambiguous, well-defined requirements | | Completeness | 25 | All functional aspects covered | | Testability | 20 | Clear acceptance criteria | | Technical Feasibility | 15 | Realistic implementation plan | | Scope Definition | 10 | Clear feature boundaries |
**Threshold**: ≥ 90 points to proceed
If initial score < 90: 1. User provides feedback 2. Agent revises requirements 3. System recalculates score 4. Repeat until ≥ 90 5. User confirms → Save → Next phase
| Aspect | Requirements Workflow | BMAD Workflow | |--------|----------------------|---------------| | **Phases** | 4 (Requirements → Code → Review → Test) | 6 (PO → Arch → SM → Dev → Review → QA) | | **Duration** | Fast (hours) | Thorough (days) | | **Documentation** | Minimal | Comprehensive | | **Quality Gates** | 1 (Requirements ≥ 90) | 2 (PRD ≥ 90, Design ≥ 90) | | **Approval Points** | None | Multiple (after PRD, Architecture, Sprint Plan) | | **Best For** | Simple features, prototypes | Complex features, enterprise projects | | **Artifacts** | 4 documents | 6 documents | | **Planning** | Direct implementation | Sprint planning included | | **Architecture** | Implicit in requirements | Explicit design phase |
/requirements-pilot "REST API endpoint for user profile updates with validation" # Generated requirements include: # - Endpoint specification (PUT /api/users/:id/profile) # - Request/response schemas # - Validation rules # - Error handling # - Authentication requirements # Implementation follows directly # Review checks API best practices # Testing includes endpoint testing
/requirements-pilot "Add audit logging table for user actions" # Generated requirements include: # - Table schema definition # - Indexing strategy # - Retention policy # - Query patterns # Implementation creates migration # Review checks schema design # Testing verifies logging behavior
/requirements-pilot "Fix race condition in order processing queue" # Generated requirements include: # - Problem description # - Root cause analysis # - Solution approach # - Verification steps # Implementation applies fix # Review checks concurrency handling # Testing includes stress tests
Each phase supports feedback:
Agent: "Requirements complete (Score: 85/100)" User: "Add error handling for network failures" Agent: "Updated requirements (Score: 93/100) ✅" ``
AI-powered development automation with multi-backend execution (Codex/Claude/Gemini/OpenCode)
Repo: cexll/myclaude
**BMAD (Business-Minded Agile Development)** - AI-driven agile development automation with role-based agents
Interactive System Architect agent for technical design with quality scoring and user confirmation
Automated Developer agent for implementing features based on PRD, architecture, and sprint plan
Repository-aware orchestrator agent for workflow coordination, repository analysis, and context management
Interactive Product Owner agent for requirements gathering with quality scoring and user confirmation