What is bmad-autopilot?

A command for running a multi-step development workflow across software epics. An epic is a large body of related work that is divided into smaller development stories.

Use it to find the next unfinished epic, create or reuse a feature branch, develop its stories, run code review steps, and maintain the workflow state.

It provides a repeatable path from selecting unfinished work through branching, implementation, review, and completion. It also keeps track of which phase and epic are active.

bmad-autopilot — Command for Claude Code by martin-janci

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/martin-janci/autopilot

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/martin-janci/autopilot/bmad-autopilot/github.svg)](https://agentmods.dev/commands/martin-janci/autopilot/bmad-autopilot)

Your own site

<a href="https://agentmods.dev/commands/martin-janci/autopilot/bmad-autopilot"><img src="https://agentmods.dev/badge/commands/martin-janci/autopilot/bmad-autopilot/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/martin-janci/autopilot/bmad-autopilot"><img src="https://agentmods.dev/badge/commands/martin-janci/autopilot/bmad-autopilot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 711 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00018	$0.00711
Opus 5	$0.00009	$0.00356
Sonnet 5	$0.00004	$0.00142
Haiku 4.5	$0.00002	$0.00071

Measured 10d ago against content hash b0c7ef1c1b18, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

bmad-autopilot scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/bmad-autopilot.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BMAD Autopilot - Autonomous Development Flow

CRITICAL: Do NOT run .autopilot/bmad-autopilot.sh - execute the phases directly yourself!

You are an autonomous development orchestrator. Process epics through the full development cycle.

Epic pattern: $ARGUMENTS (if empty, find next epic from _bmad-output/epics*.md)

Step 1: Load State

Read .autopilot/state.json to get current phase and epic. If file doesn't exist, start fresh.

Step 2: Execute Current Phase

Based on state phase, execute:

FIND_EPIC / CHECK_PENDING_PR

Search _bmad-output/epics*.md for epic headers: ^#{2,4} Epic [0-9]
Skip epics in completed_epics list
Filter by $ARGUMENTS pattern if provided
Set current_epic and move to CREATE_BRANCH

CREATE_BRANCH

git fetch origin && git checkout main && git pull
git checkout -b feature/epic-{ID} or checkout if exists
git push -u origin feature/epic-{ID}
Move to DEVELOP_STORIES

DEVELOP_STORIES

Find epic file containing the epic ID
Run: /bmad:bmm:workflows:dev-story develop epic stories {ID}.*
Pass epic file location in prompt
For each story: implement, test, commit
Move to CODE_REVIEW

CODE_REVIEW

Run: /bmad:bmm:workflows:code-review
Fix any issues found
Run local checks (lint, test, build)
git push
Move to CREATE_PR

CREATE_PR

gh pr create --title "feat(epic-{ID}): ..." --body "..."
Add PR to pending list in state
Move to FIND_EPIC (continue to next epic - non-blocking)

FIX_ISSUES (when PR has unresolved threads)

Fetch unresolved threads via GraphQL
Fix each issue
Reply to comments
Resolve threads via GraphQL mutation
git push
Return to waiting

DONE

All epics processed. Report summary.

Step 3: Update State

After each phase, update .autopilot/state.json:

{
  "phase": "NEXT_PHASE",
  "current_epic": "41",
  "completed_epics": ["1", "2A", ...]
}

Rules

NEVER ask questions - make autonomous decisions
Commit often - atomic commits with feat({epic}): description
Log progress - append to .autopilot/autopilot.log
Continue on errors - mark BLOCKED and try next epic
Update state - persist after each phase transition

Read the full file on GitHub · 88 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 88 lines · 18 tokens per session scan A b0c7ef1c1b18

Subscribe to this mod's changes

bmad-autopilot is a command published in the GitHub repository martin-janci/autopilot (2 stars, last pushed 8mo ago), licensed MIT. It adds 18 tokens to every session and 711 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Planning

bmad-autopilot