Automated (and very opinionated) BMAD pipeline orchestration for Claude Code.
Two pipeline suites — BMM (Business Model Method) and GDS (Game Dev Suite) — each with four sequential commands that drive the BMAD development lifecycle from planning through story delivery.
👀 The pipelines are quite long and token hungry (the story pipeline alone can run for more than 60 minutes). Some steps might seem redundant, but I am satisfied with the code quality and consistency I get out of this. I recommend having a Claude Code Max x5 or x20 subscription to not hit limits mid-run.
| Command | Steps | Description |
|---|---|---|
/auto-bmad-plan |
11 | Pre-implementation pipeline: product brief, PRD, validate, UX, architecture, test framework, test design, epics, readiness, project context, sprint planning |
/auto-bmad-epic-start |
1 | Start a new epic: epic-level test design |
/auto-bmad-story |
13 | Develop a story: create, validate, adversarial review, ATDD, develop, edge-case hunt, 3x code review, NFR, trace, automate, test review |
/auto-bmad-epic-end |
3 | Close an epic: trace, retrospective, project context refresh |
| Command | Steps | Description |
|---|---|---|
/auto-gds-plan |
8 | Pre-implementation pipeline: game brief, GDD, narrative design, game architecture, test framework, game test design, project context, sprint planning |
/auto-gds-epic-start |
1 | Start a new epic: epic-level game test design |
/auto-gds-story |
11 | Develop a story: create, validate, adversarial review, develop, edge-case hunt, 3x code review, performance, test automate, test review |
/auto-gds-epic-end |
2 | Close an epic: retrospective, project context refresh |
The pipelines produce the following key artifacts throughout the lifecycle:
| Pipeline | Artifacts |
|---|---|
| BMM Plan | Product brief, PRD, UX design, architecture doc, test framework, CI configuration, epics, test design, sprint plan |
| BMM Epic Start | Retro action resolution log, green baseline report, story order plan |
| BMM Story | Story file, ATDD specs, implementation code, code review report, security scan results, regression/E2E results, traceability entries |
| BMM Epic End | Aggregated epic data, traceability gate report, retrospective, next epic preview |
| GDS Plan | Game brief, GDD, narrative design, game architecture, test framework, game test design, sprint plan |
| GDS Epic Start | Epic-level game test design |
| GDS Story | Story file, implementation code, code review report, performance assessment, game test automation, test review |
| GDS Epic End | Retrospective, project context refresh |
The workflow is the same for both BMM and GDS — substitute commands as needed. Below shows the BMM variant; for GDS, replace /auto-bmad-* with /auto-gds-*. If you already have all the planning artifacts ready, you can skip the plan pipeline and go directly to step 4 or 5.
- Prepare a strong and comprehensive input for the plan pipeline — it validates readiness and won't run with a simple
Create a todo appprompt. I recommend going through a few/bmad-brainstormingand/bmad-party-modesessions first to build up enough context. If the initial input isn't ready, the plan pipeline will tell you what to improve. - Run
/auto-bmad-plan(BMM) or/auto-gds-plan(GDS) to kick off the initial planning pipeline for a new project or major initiative. - Review the generated artifacts — PRD/GDD, Architecture, UX/Narrative design, Epics, and Test Plan. Make sure they look good and adjust if necessary before moving on to implementation. You might want to go through a few iterations of
/bmad-party-modeto refine the output, since it sets the foundation for the next steps. - For each new epic, run
/auto-bmad-epic-start(BMM) or/auto-gds-epic-start(GDS) to establish a baseline and plan the story order based on the epic's goals and dependencies. - For each story within an epic, run
/auto-bmad-story(BMM) or/auto-gds-story(GDS) to develop the story from creation through delivery. - After each story, review the report generated by the story pipeline and any other BMAD artifacts, perform some manual testing, and correct course if necessary.
- At the end of an epic, run
/auto-bmad-epic-end(BMM) or/auto-gds-epic-end(GDS) to close the epic, conduct a retrospective, and preview the next epic. - Review the outputs of each pipeline run, check the generated artifacts, and make adjustments as needed. The pipelines are opinionated and automated, but they still require human judgment and iteration. Use
/bmad-bmm-correct-course(BMM) or/bmad-gds-correct-course(GDS) when big changes are needed.
ℹ️ Important: This plugin won't automate a multi-story workflow or an entire epic. Some human orchestration and judgment is still required between pipeline runs.
One-command install via npx:
npx @stefanoginella/auto-bmadOr from the marketplace inside Claude Code:
/plugin marketplace add stefanoginella/claude-code-plugins
/plugin install auto-bmad@stefanoginella-plugins --scope <project|user|local>
Scopes: project (shared with team), user (all your projects), local (personal, gitignored).
Or as a local plugin for development:
claude --plugin-dir /path/to/plugins/auto-bmad
⚠️ IMPORTANT: Without these, the pipelines might fail or produce incorrect results. Make sure they're in place before running the pipelines.
The pipelines are based on the BMAD Method workflow and relies on specific BMAD modules.
- TEA — Test Engineering Architect. Provides test strategy, test design, and ATDD capabilities used by the BMM pipelines.
- GDS — Game Dev Suite. Provides game design, game architecture, narrative design, and game testing capabilities used by the GDS pipelines.
You only need the modules for the pipeline suite you're using. TEA for BMM, GDS for GDS.
- CIS — Creative Intelligence Suite. Enhances UX design quality during the BMM plan pipeline. Without it, UX steps use baseline prompts.
From the anthropics/claude-plugins-official marketplace.
- context7 — Live documentation lookups for library APIs. Used during architecture creation (plan) and story development (story). Without it, agents rely on training data instead of current docs.
- security-guidance — Security best practice recommendations during story development.
- Any relevant
lspplugin(s) for your codebase — used during story development for linting and test feedback. They can improve the code quality and feedback loop, but are not strictly required since the pipelines also include manual lint and test steps.
jq(required) - JSON processing in bash steps. Needed by the pipelines.- Any relevant CLI tool (optional) needed by your LSP plugin(s).
The pipelines expect BMAD configuration files in the project:
For BMM pipelines:
_bmad/bmm/config.yaml— BMM configuration (output folders, artifact paths)_bmad/tea/config.yaml— TEA configuration (test artifact paths)
For GDS pipelines:
_bmad/gds/config.yaml— GDS configuration (output folders, artifact paths)
These files are normally created by the BMAD CLI when initializing BMAD in a project. The pipelines rely on the standard structure and paths defined by these configs, so custom configurations may require pipeline adjustments.
The pipelines run various bash commands (depending on the project), skills and MCP that Claude Code will prompt you to approve if they are not already approved. For the first few runs in a new project, expect several approval prompts as the allow list builds up. After that, things stabilize and the pipelines run more autonomously.
⚠️ Alternatively, you can run Claude Code in "dangerously skip permissions" mode (--dangerously-skip-permissions), but do so at your own risk — this disables all permission checks. Only use it in an isolated environment like a VM or container.