autopilot CLAUDE.md

autopilot CLAUDE.md is an instructions file for coding agents from cookys/autopilot. It costs 4,347 tokens per session, scanned A, original, MIT.

A set of project instructions for developing the autopilot plugin, including its conventions, repository purpose, and available scripts.

In plain words
What is it for?
Use it when modifying autopilot, choosing between shell, JavaScript, or Python for a script, or checking whether an existing script already handles a task.
Why use it?
It gives coding agents the local rules and script inventory needed to make consistent changes in that repository.

Instructions file

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.

agentmods
npx agentmods add instructions/cookys/autopilot/claude-md
Clone the repo
git clone --depth 1 https://github.com/cookys/autopilot

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 autopilot CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cookys/autopilot/claude-md.svg)](https://agentmods.dev/instructions/cookys/autopilot/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cookys/autopilot/claude-md"><img src="https://agentmods.dev/badge/instructions/cookys/autopilot/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,347 This file is loaded in full into every session.
When invoked 4,347 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.04347 $0.04347
Opus 5 $0.02174 $0.02174
Sonnet 5 $0.00869 $0.00869
Haiku 4.5 $0.00435 $0.00435

Measured today against content hash 495fa4ec0a2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

autopilot CLAUDE.md 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 today.

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.

CLAUDE.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

autopilot — project conventions (Claude Code)

For Claude Code sessions working on the autopilot plugin itself. Skill-runtime conventions live in each skill's SKILL.md; this file covers cross-cutting things a session needs at entry.

For non-Claude-Code agents (OpenCode, Codex, Antigravity, …), see AGENTS.md for the agents.md-spec readme that applies to any agent. For cross-platform portability details (what each platform actually supports vs. what's unverified), see references/multi-agent-portability.md.

What this repo is

Standalone lifecycle orchestration plugin: 29 skills, 3 methodology agents, 27 hooks (14 default-on, 13 opt-in). Optional integrations and coexistence rules: docs/coexistence.md.

Scripts inventory (prefer over LLM judgment)

scripts/ ships deterministic tooling that the skills reference instead of asking the LLM to do mechanical work each run. Before hand-coding any mechanical step, check whether a script already covers it.

What each one does — purpose, when to call it, pointer to its contract — lives in docs/scripts-inventory.md. That file is the canonical index; the grouped names below exist so a session knows what to go looking for without loading 30 KB of descriptions at every startup. Most answer <script> --help — but 37 do not parse argv at all, and a few of those are installers that act immediately, so --help runs them. Check the header comment first when a script is unfamiliar. JSON emitters have stable schemas with exit codes documented in their own header.

A caution learned the hard way (2026-08-06): several of these were fully built, tested and documented, yet doing nothing — an age threshold left at 0, a hook never installed, a scanner keyed on an id the residue did not carry. A script existing is not evidence it is running. When one is supposed to be protecting something, check that it actually fires. It is one of a family — a module with zero callers, a suite that passes when you delete the gate it tests, a shadow derived from the answer it checks, an assertion pinned to one machine, a green test writing fixture rows into the real store. Each incident and its preventing artifact: references/evidence-discipline.md. Read it before recording anything as verified.

Read the full file on GitHub · 147 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. today Changed · +51 tokens per session 495fa4ec0a2b
  2. 4d ago First seen · 147 lines · 4,296 tokens per session scan A f47aad8faa2f

Subscribe to this mod's changes

autopilot CLAUDE.md is an instructions file published in the GitHub repository cookys/autopilot (11 stars, last pushed today), licensed MIT. It adds 4,347 tokens to every session, about $0.0217 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 instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens