agentmods.dev

bmad-autopilot-skill

bmad-autopilot-skill is a skill for Claude Code from martin-janci/autopilot. It costs 43 tokens per session (801 once invoked), scanned A, original, MIT.

An autonomous development workflow for processing software epics, which are larger features made up of smaller development stories. It coordinates development, review, pull-request creation, and continuation across epics.

In plain words
What is it for?
Use it to process all or selected epics, resume an interrupted run, create branches and pull requests, and automate the BMAD development cycle.
Why use it?
It removes much of the manual coordination needed to take an epic from selection through coding, review, and a pull request.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./.autopilot/bmad-autopilot.sh.

not rated 2repo 8mo ago A scan 43 tokens original MIT

Good fit Use it to process all or selected epics, resume an interrupted run, create branches and pull requests, and automate the BMAD development cycle.

Compare 6 skills from other repositories ↓
View source ↗ martin-janci/autopilot
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/martin-janci/autopilot
agentmods
npx agentmods add skills/martin-janci/autopilot/bmad-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.

agentmods badge for bmad-autopilot-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/martin-janci/autopilot/bmad-autopilot/github.svg)](https://agentmods.dev/skills/martin-janci/autopilot/bmad-autopilot)
Your own site
<a href="https://agentmods.dev/skills/martin-janci/autopilot/bmad-autopilot"><img src="https://agentmods.dev/badge/skills/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.

agentmods 80×15 button for bmad-autopilot-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/martin-janci/autopilot/bmad-autopilot"><img src="https://agentmods.dev/badge/skills/martin-janci/autopilot/bmad-autopilot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 801 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.00801
Opus 5 $0.00022 $0.00400
Sonnet 5 $0.00009 $0.00160
Haiku 4.5 $0.00004 $0.00080

Measured 11d ago against content hash 1754982d74c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

bmad-autopilot-skill 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 11d 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.

skills/bmad-autopilot/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BMAD Autopilot - Autonomous Development Orchestrator

This skill runs the BMAD Autopilot bash orchestrator to automatically process epics through the full development cycle.

When to Use

Activate this skill when the user:

  • Wants to run the autopilot or orchestrator
  • Asks to process epics automatically
  • Mentions BMAD development workflow
  • Wants to automate PR creation and review cycles

Execution

Run the orchestrator from the repository root:

# Process ALL epics automatically
./.autopilot/bmad-autopilot.sh

# Process specific epics
./.autopilot/bmad-autopilot.sh "7A 8A"

# With verbose output
./.autopilot/bmad-autopilot.sh --verbose

# Resume after interruption
./.autopilot/bmad-autopilot.sh --continue

Workflow States

The orchestrator runs through these phases:

  1. CHECK_PENDING_PR - Find unfinished PRs
  2. FIND_EPIC - Select next epic to process
  3. CREATE_BRANCH - Create feature branch
  4. DEVELOP_STORIES - Claude develops the epic (interactive)
  5. CODE_REVIEW - Run local checks and review (interactive)
  6. CREATE_PR - Create pull request
  7. → Auto-continue to next epic (PR added to pending list)
  8. Background: Pending PRs monitored, auto-merged when ready
  9. FIX_ISSUES - If Copilot has comments, fix and resolve threads
  10. MERGE_PR - Merge when CI passes and approved
  11. Loop until all epics DONE

Auto-Approve Integration

The auto-approve.yml GitHub workflow handles PR approval with strict conditions:

Approval conditions (ALL must be met):

  1. At least 10 minutes since last push
  2. Copilot review exists
  3. All review threads resolved
  4. All CI checks passed

Flow:

  1. After PR creation - Autopilot continues to next epic immediately
  2. Copilot reviews - Triggers auto-approve workflow
  3. Workflow waits for CI - Polls until all checks pass
  4. Workflow checks conditions - 10 min wait, threads resolved
  5. Dismisses stale approvals - If unresolved threads exist
  6. Approves only when ready - All conditions met
  7. PR becomes mergeable - Autopilot's background check merges it

Read the full file on GitHub · 100 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.

  1. 11d ago First seen · 100 lines · 43 tokens per session scan A 1754982d74c8

Subscribe to this mod's changes

bmad-autopilot-skill is a skill published in the GitHub repository martin-janci/autopilot (2 stars, last pushed 8mo ago), licensed MIT. It adds 43 tokens to every session and 801 once invoked, about $0.0002 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 agentsPlanning
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens