stefanoginella/auto-bmad
5 stars · Last commit 2026-05-31
BMAD module that drives the full BMAD story workflow end-to-end, one story at a time, on Claude Code or Codex — delegating each step to model/effort-tuned subagents.
README preview
# auto-bmad [](./LICENSE) [](https://github.com/stefanoginella/auto-bmad) [](https://github.com/bmad-code-org/BMAD-METHOD) [](https://github.com/bmad-code-org/BMAD-METHOD) [](#install) [](./CONTRIBUTING.md) A **BMAD module** that runs the **full [BMAD](https://github.com/bmad-code-org/BMAD-METHOD) story implementation workflow end-to-end — one story at a time**, on **Claude Code or Codex**. `auto-bmad` chains the core BMM skills (`create-story` → `dev-story` → `code-review`) and the optional TEA (Test Architect) skills into a single resumable pipeline. It detects the next story from `sprint-status.yaml` (or takes one as an argument), runs every step in an isolated git branch with conventional-commit checkpoints, opens a PR, and finishes with a report of the PR link, open questions, deferred work, and anything that needs your attention — then stops so **you** decide when to start the next story. The orchestrator **only delegates and reports.** Every BMAD step runs inside a sub-agent, with the model and thinking effort matched to the stakes of the step (e.g. Opus/max for high-stakes implementation, a faster model for low-stakes mechanics). On **Claude Code and Codex** those delegates are real, tuned subagents (`.claude/agents` / `.codex/agents`, generated from a configurable profiles block); on a tool with generic subagents it falls back to those (untuned), and on one with none it runs steps inline — same pipeline either way. > Requires the BMAD skills it orchestrates (`bmm`, plus `tea` for the test phases) and a `_bmad/` config in your project — the installer below can add these in the same run. auto-bmad drives those skills; it does not replace them. > **Compatibility:** tested against the **[BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD) v6 skill line**, currently up to **6.8.0** (and the **6.8.1-next.0** prerelease). > ⚠️ **It can't save you from bad inputs.** auto-bmad automates the *workflow*, not judgment — the quality of what comes out is capped by what goes in. Vague epics, thin acceptance criteria, or a shaky architecture produce vague, untrustworthy code, just faster and more confidently. The automated code-review loop and the human-in-the-loop stops below are guardrails, not guarantees; the real leverage is clear stories and a sound design *before* you press go. Garbage in, garbage out. ## Install auto-bmad is a BMAD module, so the official way to install it — for **any** supported tool, Claude Code included — is the **BMAD installer**. Requires **Node.js 20.12+** and Git.