By bspann
BMad Method for Claude Cowork — AI-driven agile development with specialized agents, structured workflows, and test architecture. Includes BMM (core dev lifecycle), BMB (agent/workflow builder), and TEA (test engineering architect) modules.
Quick Flow: streamlined spec-build-review for bug fixes and small features.
Create system architecture from an approved PRD. Phase 3 (Solutioning).
Create a project brief from a product idea. Phase 1 (Analysis).
Implement a story using red-green-refactor TDD. Phase 4.
Break architecture into epics and stories with acceptance criteria. Phase 3.
Use when exploring a product idea, creating a project brief, or conducting discovery research. Specializes in market analysis, problem-space exploration, and translating vague ideas into structured briefs. Trigger with: "analyze my idea", "create a project brief", "explore this concept", "discovery research"
Use when designing system architecture, selecting tech stack, defining data models, or creating API contracts. Specializes in translating PRDs into technical architecture documents. Trigger with: "create architecture", "design system", "tech stack", "data model", "API design"
Use when creating custom BMad agents, workflows, or modules. The meta-agent that extends the BMad ecosystem. Trigger with: "create agent", "create workflow", "build module", "extend BMad", "custom agent"
Use when reviewing code for quality, correctness, security, and adherence to architecture. Adversarial reviewer that finds 3-10 issues minimum per review. Trigger with: "code review", "review code", "review story", "review PR"
Use when implementing stories, writing code, creating tests, or fixing bugs. Follows red-green-refactor TDD methodology with task-by-task verification. Trigger with: "implement story", "dev story", "write code", "implement feature", "fix bug"
Design system architecture from an approved PRD. Phase 3 (Solutioning).
Create a project brief from a product idea. Phase 1 (Analysis) of the BMad Method.
Design and create a new custom BMad agent with persona, expertise, and workflows.
Create a complete BMad module packaging agents, workflows, and knowledge together.
Design and create a new BMad workflow with steps, templates, and checklists.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Cowork plugin that brings the BMad Method to Anthropic's desktop agent. Ship production-quality software with specialized AI agents — Analyst, PM, Architect, Developer, Code Reviewer, Test Architect, and more — all orchestrated from Claude Cowork or Claude Code.
The BMad Method is a structured, AI-driven approach to software development. It uses specialized agent personas to take a product idea through a complete lifecycle:
Brief → PRD → Architecture → Stories → Implementation → Review → Ship
This plugin adapts BMad to run natively as a Claude Code / Cowork plugin, using:
| Module | Agents | Workflows | Purpose |
|---|---|---|---|
| BMM (Core) | 8 agents | 16 workflows | Full development lifecycle: analysis → planning → architecture → implementation |
| TEA | 1 agent (Murat) | 9 workflows | Risk-based test strategy, automation, CI, release gates |
| BMB | 1 agent (Brix) | 3 workflows | Create custom agents, workflows, and modules |
Option A: From a marketplace (when published)
claude plugin install bmad-cowork
Option B: Local install from GitHub
git clone https://github.com/YOUR_USERNAME/bmad-cowork.git
cd your-project
claude --plugin-dir /path/to/bmad-cowork
Option C: Test locally during development
claude --plugin-dir ./bmad-cowork
/bmad-cowork:init to scaffold your project/bmad-cowork:help to see what to do next/bmad-cowork:init # Set up project structure
/bmad-cowork:brief # Create project brief (Phase 1)
/bmad-cowork:prd # Create PRD (Phase 2)
/bmad-cowork:architect # Design architecture (Phase 3)
/bmad-cowork:ux-design # UX design spec (Phase 3, optional)
/bmad-cowork:epics # Create epics & stories (Phase 3)
/bmad-cowork:ready # GO/NO-GO readiness check
/bmad-cowork:sprint-plan # Plan Sprint 1 (Phase 4)
/bmad-cowork:dev # Implement a story
/bmad-cowork:review # Code review
/bmad-cowork:retro # Sprint retrospective
/bmad-cowork:quick-dev # Spec → Build → Review in one workflow
/bmad-cowork:status # Where am I? What's next?
/bmad-cowork:help # Interactive guidance
| Agent | Name | Specialty |
|---|---|---|
| Analyst | Alex | Market analysis, project briefs, discovery research |
| PM | Patricia | PRDs, requirements, user journeys, MVP scoping |
| Architect | Archie | System design, tech stack, data models, APIs, security |
| UX Designer | Uma | Screen specs, user flows, component libraries, accessibility |
| Scrum Master | Sam | Epics, stories, sprint planning, status tracking, retrospectives |
| Developer | Devon | TDD implementation, red-green-refactor, task-by-task coding |
| Code Reviewer | Cora | Adversarial review (3-10 issues minimum), APPROVE/REQUEST_CHANGES |
| TEA | Murat | Test strategy, automation, frameworks, CI, release gates |
| Quick Flow | Barry | Rapid bug fixes and small features without full planning |
| BMad Builder | Brix | Create custom agents, workflows, and modules |
| Tech Writer | Tanya | API docs, user guides, README, project documentation |
npx claudepluginhub bspann/bmad-cowork --plugin bmad-coworkComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.