Alex Verkhovsky
ea668933c8
The content under review is staged exactly once as a file, and layer and
lens prompts carry its absolute path instead of the diff bytes. The parent
no longer regenerates the diff into every child prompt, which is what made
launch prompts large and staggered their dispatch.
bmad-build and bmad-build-auto stage the diff in step-03, before the
acceptance/verification check, and read it there so that check judges the
diff rather than the implementation subagent's report; a code change during
the check rewrites and re-reads it. Step-04 restages and hands the layers
the path. Staged files are uniquely named in the system temp directory so
concurrent runs cannot collide — bmad-code-review's staged diff moves there
too, off the fixed path it shared between runs.
bmad-review states the same contract once in its dispatch, covering every
lens: stage a branch, uncommitted work, or a commit range to one file and
pass the path. A branch means the diff against the merge base; uncommitted
work includes untracked files.
Inlining survives only in bmad-build's no-subagents fallback, where the
prompt is pasted into a session that shares no filesystem with this one. It
inlines every file the prompt points to and leaves every other line alone,
so the reviewer constraints that follow the content label survive.
Also carries the claims falsification pass to the build skills, adapted
rather than copied. In bmad-code-review the claims mechanism recovers a
narrative the skill does not own, so it guards on whether a claims file was
supplied. Build wrote the spec and ran the implementer, so there is no such
asymmetry: {claims_file} is {spec_file}, the check is unconditional, and it
reads only the Intent and Tasks & Acceptance sections. The reviewer's own
asymmetry survives — it is context-free by design and still opens the spec
for the first time after its independent path tracing.
Agile Ai Driven Development — turn an idea or change request into working software without giving up the thinking.
Ai Driven Development (AiDD) covers the whole effort, not only the code: what to build, how it holds together, and how it changes as you learn. BMad Method is the agile way to do it — decisions stay explicit, context carries forward, and the process sizes itself to the work. Small changes go straight to build. Complex work gets the depth it needs. The same method covers a weekend prototype and a system with years of history behind it.
Start anywhere. Use BMad end to end, or carry its briefs, specifications, and architecture into your existing delivery workflow.
Start Building
Prerequisites: Node.js 20.12+, Python 3.10+, and uv
npx bmad-method install
Open your project in your AI coding tool, invoke bmad-build with what you want to change, and keep making the decisions that matter. Run bmad-help whenever you want guidance on what comes next or what is optional.
Build your first project with BMad →
Add BMad to an existing codebase →
BMad is free and open source, with no paywalled workflows or gated community. For prerelease builds, CI/CD, configuration overrides, and non-interactive setup, see the installation guide.
Why BMad?
Coding assistants are effective at implementation, but they often turn unstated assumptions into code. BMad keeps you in control while its agents and workflows make the important decisions explicit and preserve them as context for the work that follows.
- Right-sized process — Go directly to implementation for clear changes or add deeper planning for larger initiatives.
- New or existing code — Start from nothing, or establish verified context on a codebase you inherited and work from what is actually there.
- Durable context — Carry product and technical decisions forward instead of re-explaining them in every chat.
- Specialized perspectives — Bring in product, architecture, UX, development, and testing expertise when it helps.
- Guided collaboration — Use structured workflows and multiple-agent discussions without handing over judgment.
- One delivery path — Move from early thinking through reviewed implementation, correction, and learning.
See how the workflows fit together →
BMad Ecosystem
Install the core method or add official modules for specialized work.
| Module | Purpose |
|---|---|
| BMad Method | Plan and deliver software, from new prototypes to established codebases |
| BMad Builder | Skill, workflow, and agent builder |
| BMad Creative Intelligence Suite | Creative thinking partners for innovation, design thinking, and storytelling |
| BMad Test Architect | Enterprise testing add-on for BMad Method |
| BMad Loop | Builds, verifies, and retros a whole epic unattended |
| BMad Game Dev Studio | Ideate, design, and build games in any framework, including Unity, Unreal, Godot, and Phaser |
Plan on the Web
Web bundles package selected BMad workflows as Google Gemini Gems and ChatGPT Custom GPTs. Use them for planning in your existing web subscription, then bring the resulting artifacts into your AI coding tool for implementation.
Documentation
- Getting Started — Install BMad and build a small project.
- Workflow Map — Understand the available paths and outputs.
- Established Projects — Add BMad to an existing codebase.
- Upgrade to V6 — Migrate from an earlier version.
Roadmap
See what is in progress and what is planned on the public roadmap.
Community
- Discord — Get help, share ideas, and collaborate.
- YouTube — Watch tutorials and master classes.
- GitHub Issues — Report bugs and request features.
- GitHub Discussions — Join longer community conversations.
- BMad Code — Explore the wider ecosystem.
Support and Contributing
BMad is free for everyone and always will be. Star the repository, buy me a coffee, or email contact@bmadcode.com for corporate sponsorship.
Contributions are welcome. Read CONTRIBUTING.md before opening a pull request.
License
MIT License — see LICENSE for details.
BMad and BMAD-METHOD are trademarks of BMad Code, LLC. See TRADEMARK.md for details.
See CONTRIBUTORS.md for contributor information.
