chief-autopilot

chief-autopilot is a skill for Claude Code from thaitype/chief. It costs 70 tokens per session (862 once invoked), scanned A, original, MIT.

An automatic work loop for chief-agent, a coding agent that plans tasks, delegates them to a builder, and repeats until a milestone is complete. It supports a fully automatic mode and a safe mode that pauses when a design choice is unclear.

In plain words
What is it for?
Use it to execute an existing milestone from its goals and contracts, create or update a task list, and delegate batches of three to five tasks until the milestone is done.
Why use it?
It removes the need to manually start each batch of coding tasks. Before running, it checks that written goals and contracts—rules describing the expected work—exist.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions AGENTS.md.

Part of the chief-skills plugin — 14 skills shipped together

Good fit Use it to execute an existing milestone from its goals and contracts…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thaitype/chief/chief-autopilot
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.

Any agent
npx skills add thaitype/chief --skill chief-autopilot
Clone the repo
git clone --depth 1 https://github.com/thaitype/chief

Made for: Claude Code.

Or install chief-skills, the plugin that ships this one along with the rest of its 14 skills.

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 chief-autopilot

README.md
[![agentmods](https://agentmods.dev/badge/skills/thaitype/chief/chief-autopilot.svg)](https://agentmods.dev/skills/thaitype/chief/chief-autopilot)
Your own site
<a href="https://agentmods.dev/skills/thaitype/chief/chief-autopilot"><img src="https://agentmods.dev/badge/skills/thaitype/chief/chief-autopilot.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 862 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 $0.00070 $0.00862
Opus 5 $0.00035 $0.00431
Sonnet 5 $0.00014 $0.00172
Haiku 4.5 $0.00007 $0.00086

Measured 7d ago against content hash b212dc6cf37d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

chief-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 7d 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/chief/chief-autopilot/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run the chief-agent autonomously on the current milestone.

Arguments

  • No argument or autoauto mode (default). Chief makes all decisions, never stops for human input.
  • safesafe mode. Chief stops when ambiguity requires a design decision.

Prerequisite Check

Before doing anything:

  1. Identify the active milestone directory under .chief/.
  2. Check that _goal/ has at least one non-empty file.
  3. Check that _contract/ has at least one non-empty file.

If either is missing → STOP. Tell the user:

"Goals and contracts are required for autopilot. Run /chief-plan first."

Do NOT proceed.

Entry Confirmation

Present the current goals and contracts to the user in a brief summary (file names + 1-line description each).

Ask one question:

"Goals and contracts look correct? Proceed with full automation, or use /chief-plan to revise first?"

If the user says revise → stop. If the user confirms → proceed.

Execution Loop

1. Create or update TODO

Read existing _plan/_todo.md if present. Create the next batch of 3–5 tasks based on goals, contracts, and what's already done.

Write _plan/_todo.md. Do NOT wait for approval — this is autopilot.

2. Delegate to builder-agent

For each uncompleted task in _todo.md:

  • Delegate to builder-agent with:
    • The TODO entry
    • Milestone goals (_goal/)
    • Milestone contracts (_contract/)
    • Relevant global rules (.chief/_rules/)
    • Verification expectations
  • Wait for builder to complete
  • Mark task [x] in _todo.md when done

3. Handle blockers and ambiguity

Auto mode:

  • If builder reports a blocker or ambiguity → chief-agent picks the best option and continues.
  • Document the decision in the batch report (see below).
  • Builder-agent should escalate to chief-agent when possible before giving up.

Safe mode:

  • If builder reports a blocker or ambiguity → STOP and present the issue to the user with options.
  • Wait for user decision, then continue.

4. Repeat

Read the full file on GitHub · 119 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. 7d ago First seen · 119 lines · 70 tokens per session scan A b212dc6cf37d

Subscribe to this mod's changes

chief-autopilot is a skill published in the GitHub repository thaitype/chief (59 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 862 once invoked, about $0.0003 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 2026-08-30.

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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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