Sandbox
@aj-geddes/claude-code-bmad-skills

BMAD planning plugin for Claude Code

This plugin adds BMAD Method planning and orchestration to Claude Code through a packaged plugin. It organizes work into analysis, planning, solutioning, and implementation handoff, then produces a `ready-for-dev` story and handoff manifest for another tool to pick up.

485 stars75 forksShellUpdated 2mo ago
Who it's for

Builders who use Claude Code and want their agent to plan work before implementation.

What it delivers

You can break work into safe parallel streams and hand it off without re-explaining the plan.

What it does

BMAD lifecycle

Runs Analysis → Planning → Solutioning → Implementation-handoff as a guided flow.

Track-based workflow

Supports Quick Flow, BMad Method, and Enterprise tracks to fit the size of the work.

Parallel workstream planning

Scopes stories to disjoint files and orders them into waves to reduce merge conflicts.

Handoff manifest

Creates `handoff-manifest.json` so another dev runner can continue the work.

Plugin distribution

Ships as a Claude Code marketplace plugin instead of a manual skills install.

How to get it

  1. 1Run
    /plugin marketplace add aj-geddes/claude-code-bmad-skills
    /plugin install bmad-planning-orchestrator@bmad-method-harness

README

BMAD Planning & Orchestrator — a Claude Code plugin

Run in Smithery BMAD Method License: MIT

This repository is a Claude Code plugin marketplace. It ships one plugin — BMAD Planning & Orchestrator — that harnesses the BMAD Method to plan, document, and orchestrate software work as conflict-free parallel workstreams, then hands implementation off to your dev tools.

It plans and orchestrates. It does not write the code.

Documentation site: https://aj-geddes.github.io/claude-code-bmad-skills


🎯 Attribution & Credit

The BMAD Method™ (Breakthrough Method for Agile AI-Driven Development) is created and maintained by the BMAD Code Organization. This repository is an independent Claude Code harness for the method — not an official BMAD product, and no endorsement is implied. All methodology credit belongs to the BMAD Code Organization.

The methodology, agent roles, workflow patterns, document shapes, and all BMAD concepts are the intellectual property of the BMAD Code Organization. See bmad-planning-orchestrator/ATTRIBUTION.md.


Install

/plugin marketplace add aj-geddes/claude-code-bmad-skills
/plugin install bmad-planning-orchestrator@bmad-method-harness

Then /reload-plugins (or restart Claude Code). That's it — no installer script, no npx, no copying into ~/.claude. Updates flow through the marketplace.

Local development: claude --plugin-dir ./bmad-planning-orchestrator


What you get

The plugin runs the BMAD lifecycle — Analysis → Planning → Solutioning → Implementation-handoff — right-sized by an interactive track (Quick Flow / BMad Method / Enterprise), and stops at a ready-for-dev story file plus a tool-agnostic handoff manifest.

Its signature contribution is making parallel AI development safe:

  • One architecture prevents semantic conflicts (API style, data model, naming, security) across agents.
  • Stories scoped to disjoint files, dependency-ordered into parallel waves, prevent file/merge conflicts.
  • handoff-manifest.json lets any dev runner pick up the work.

Full skill catalog, flow diagram, and the handoff contract are in the plugin README: bmad-planning-orchestrator/README.md.


Why a plugin (and why planning-only)?

This project began as a suite of Claude Code skills installed by a bash/ PowerShell script. Two things changed:

  1. Claude Code added plugins + marketplaces — a first-class way to distribute and version a bundle of skills, agents, and hooks. We adopted it.
  2. The BMAD Method advanced to a skills-centric v6.x and the broader ecosystem grew capable dev tools. So we refocused: BMAD does what it is best at — planning and orchestration — and lets specialized tools do the coding. The developer/dev-story/lint/coverage pieces were removed.

If you used the old skills install, see MIGRATION.md.


Repository layout

claude-code-bmad-skills/
├── .claude-plugin/
│   └── marketplace.json          # the marketplace (one plugin)
├── bmad-planning-orchestrator/   # ← the plugin
│   ├── .claude-plugin/plugin.json
│   ├── skills/                   # 20 planning/orchestration skills
│   ├── agents/                   # planning subagents
│   ├── hooks/                    # next-step nudges
│   ├── scripts/  resources/      # shared utils + guides
│   ├── README.md  ATTRIBUTION.md  LICENSE  CHANGELOG.md
├── docs/                         # GitHub Pages site
├── CLAUDE.md  CONTRIBUTING.md  MIGRATION.md  LICENSE

Contributing

See CONTRIBUTING.md. The one rule that defines this project: every contribution stays on the planning/orchestration side of the line — nothing here writes, runs, tests, or reviews application code.

License

MIT — see LICENSE. The BMAD Method™ name and methodology belong to the BMAD Code Organization; this license covers only the Claude Code plugin implementation.

Files in the repo

Repository payload9 top-level entries
  • .claude-plugin
  • bmad-planning-orchestrator
  • docs
  • .gitignore
  • CLAUDE.md
  • CONTRIBUTING.md
  • LICENSE
  • MIGRATION.md
  • README.md

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More plugins

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

138k
1 add

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

82k
code-yeongyu/
oh-my-openagent

OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.

69k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

94k

Opinionated Oxlint rules for rejecting low-evidence TypeScript and JavaScript patterns

4.3k