By aj-geddes
Run the BMAD planning lifecycle to produce structured artifacts (brainstorm, research, product brief, PRD, SPEC, architecture, UX, epics, stories) and then orchestrate conflict-free, dependency-ordered parallel workstreams for handoff to dev tools. Plans and orchestrates; never writes code.
PLANNING SUBAGENT — scopes ONE epic into an ordered list of stories with disjoint Owned File/Module Scope boundaries, making the epic's stories safe for parallel execution by the story-author subagents that follow. Receives: one epic's requirements slice (from epics.md or the PRD cluster), the architecture document, and any already-scoped epics (to avoid cross-epic collisions). Produces: a scoping manifest for the epic — story titles, one-line intents, proposed Owned File/Module Scopes, dependency order, and a sizing verdict per story — ready for the orchestrator to fan out to story-author agents. Use when the orchestrator says "scope epic {N}", "enumerate stories for epic {N}", "what stories does epic {N} need", or "build the story list for {slug}". This agent NEVER writes story files, application code, tests, or lint. Its sole output is a scoping manifest — a planning artifact the orchestrator uses to drive story-author subagents.
PLANNING SUBAGENT — independently audits one or more planning artifacts and returns a structured verdict of PASS, CONCERNS, or FAIL with itemized findings. Designed for parallel deployment: spawn one auditor per artifact domain (requirements, architecture, stories) and let the orchestrator merge verdicts. Use when the orchestrator says "audit the PRD", "audit the architecture", "audit story {N}", "run an independent audit", "check artifact readiness", "gate-check before story compilation", or "validate planning artifacts independently". This agent reads planning documents ONLY. It NEVER writes application code, runs tests, lints, builds, or reviews implementation diffs. Its sole output is an audit report and a PASS / CONCERNS / FAIL verdict that the orchestrator uses to decide whether to proceed, ask for fixes, or block the workflow.
PLANNING SUBAGENT — compiles ONE story file as a fully source-cited context object in isolation. Receives a single story assignment (epic number, story number, slug, and the shared sharding-context path) and produces one {epic}.{story}.{slug}.story.md that is self-contained (~8K tokens) and ready for the orchestrator's scope-conflict check. Spawned by the bmad-epics-and-stories skill when fanning out story compilation across parallel agents. Use when the orchestrator says "compile story {epic}.{story}" or "author the story file for {slug}". This agent NEVER writes application code, runs tests, lints, builds, or reviews diffs. Its sole output is a planning artifact — the story file. Implementation is handed to external dev tools after the orchestrator marks the story ready-for-dev.
Solutioning skill (Winston, the Architect). Produces architecture.md with ADRs and systematic NFR coverage, mapping every FR/NFR from the PRD to a concrete design decision. ONE architecture forces all future parallel dev agents to share the same API style, data model, state management, naming conventions, and security approach — catching alignment here is 10x cheaper than during implementation. Use when the user says "design the architecture", "create architecture", "/architecture", "solutioning", "tech stack", "system design", "ADR", "architecture decision record", "data model", "API design", "NFR coverage", "non-functional requirements", or after a PRD is done and they ask "what's next" / "ready for solutioning". Supports Create (new architecture.md), Update (revise against PRD changes), and Validate (check coverage + ADR completeness). PLANS only — never writes application code, runs tests, lints, or builds.
Facilitates structured ideation sessions using proven brainstorming techniques (SCAMPER, SWOT, 5 Whys, Mind Mapping, Six Thinking Hats, Reverse Brainstorming, Starbursting, Brainwriting). Produces a brainstorming-report.md of organized ideas and actionable insights. Operates in three intents: Create (new session), Update (add techniques or deepen coverage), Validate (confirm insights align with project goals). Use when the user says: "brainstorm", "ideate", "generate ideas", "explore options", "SCAMPER", "SWOT analysis", "mind map", "Six Thinking Hats", "5 Whys", "creative session", "what if we", "let's explore", "think through possibilities", "find alternatives", or "problem-solve". This skill PLANS only — it never writes application code or runs tests.
Meta-skill for scaffolding and validating custom PLANNING/ORCHESTRATION skills within the BMAD Planning & Orchestrator plugin. Produces the full skill directory: SKILL.md, scripts, and templates — all pre-targeted at this plugin's path conventions. Includes a scope-violation checker so newly created skills never drift into dev/lint/build/coverage territory. Use when the user says "create a skill", "scaffold a skill", "build a new planning skill", "add a skill to the orchestrator", "extend BMAD planning", "custom orchestration skill", "validate this skill", "check this skill for scope violations", "new skill for the planner", or "bmad-builder". Supports three intents: Create (new skill skeleton), Validate (check an existing SKILL.md), Scaffold (directory structure only). This skill plans and scaffolds only — it NEVER writes application code, runs tests, lints, or builds.
CROSS-PHASE mid-stream scope correction. Re-enters planning when requirements, features, architecture, or constraints change after planning has started. Re-shards affected epics/stories, re-sequences sprint-status.yaml, appends rationale to decision-log.md. Routes to bmad-epics-and-stories, bmad-sprint-planning, or bmad-parallel-plan as needed. Changes the PLAN, never code. Use when: "we need to change course", "scope has changed", "new requirement came in", "we're dropping feature X", "we need to pivot", "re-plan after the change", "requirements changed mid-sprint", "correct course", "architecture changed", "re-scope the backlog", "update epics after feedback", "cancel story X", "add epic for Y", "change the plan", "we got new constraints", or when stories are split/merged/reordered due to a decision not in the original plan. Produces: updated epics.md (affected only), revised/new story files, updated sprint-status.yaml, new decision-log.md entry. NEVER writes code or runs tests.
BROWNFIELD planning input. Scans an existing codebase READ-ONLY and writes project-documentation.md — ground truth for stack, structure, key flows, conventions, and integration points — so downstream BMAD planning skills start from reality. Does NOT modify code; produces only the doc artifact. Use when the user says: "document this codebase", "document the project", "document my app", "scan the existing code", "brownfield planning", "we have existing code, start planning", "map what's already built", "document current state", "capture the current architecture", "understand the existing system before planning", "write project-documentation.md", or before a PRD or architecture doc when the user already has code written. Three intents: Create (initial scan), Update (re-scan changed areas), Validate (check completeness). Plans only — reads code but never writes it, runs no tests, no linters, no build tools, no application code.
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 claimnpx claudepluginhub aj-geddes/claude-code-bmad-skills --plugin bmad-planning-orchestratorBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
This plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.
maxParallelDefault maximum number of stories planned to run concurrently in a parallel wave (your dev tool enforces the actual concurrency).
${user_config.maxParallel}defaultTrackPreferred planning track when not chosen interactively: quick-flow, bmad-method, or enterprise. Leave blank to always choose interactively.
${user_config.defaultTrack}outputFolderDirectory (relative to your project) where BMAD planning artifacts are written.
${user_config.outputFolder}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
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.
/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
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:
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.
This project began as a suite of Claude Code skills installed by a bash/ PowerShell script. Two things changed:
developer/dev-story/lint/coverage pieces were removed.If you used the old skills install, see MIGRATION.md.
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
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.
MIT — see LICENSE. The BMAD Method™ name and methodology belong to the BMAD Code Organization; this license covers only the Claude Code plugin implementation.
Agent orchestration for Claude Code: 5 subprocess agents + 14 composable skills with cost-aware model tiering (fable/opus/sonnet/haiku), MCP-aware routing, and workflow fan-out. Agents spawn with fresh 200K context windows for true context isolation.
BMAD Method - Breakthrough Method for Agile AI-Driven Development
Next level skills for power users — advanced prompting techniques, agent management, and more.
BMAD Skills collection for Claude Code
BMAD 全自动项目编排插件。从需求到部署的完整研发流水线,编排 9 个专业 Agent(PM、架构师、UI 设计师、Tech Lead、Scrum Master、开发者、QA、DevOps)自动完成完整研发周期。
RalphMAD — Autonomous BMAD-METHOD workflow execution via ralph-loop. Templatized prompts that auto-populate from project context for reusable, project-agnostic SDLC automation.
Harness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses