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.
npx agentmods add instructions/cookys/autopilot/agents-mdgit clone --depth 1 https://github.com/cookys/autopilotWhat 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 | $0.03191 | $0.03191 |
| Opus 5 | $0.01596 | $0.01596 |
| Sonnet 5 | $0.00638 | $0.00638 |
| Haiku 4.5 | $0.00319 | $0.00319 |
Grade A, and why
autopilot AGENTS.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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
autopilot — Agent Instructions
This file follows the agents.md convention: a single agent-facing readme that any coding agent (Claude Code, OpenCode, Codex, Antigravity, Cursor, Aider, …) can read on entry to this repository. Sections below follow the spec's recommended four-section structure (Project Structure / Coding Conventions / Testing / PR Guidelines) plus two autopilot-added sections (Build / Contribution).
For Claude Code-specific conventions, see CLAUDE.md. For cross-agent portability detail (what each platform actually supports vs. what's unverified), see references/multi-agent-portability.md.
Project Structure (spec)
skills/ 29 lifecycle/methodology skills (SKILL.md format)
agents/ 3 methodology agents (reviewer, debugger, planner) — markdown body + YAML frontmatter
hooks/ Claude Code hooks (bash + JS) and hooks.json manifest
platforms/codex/ Codex skills + production PostCompact package + repo-local marketplace
.opencode/ OpenCode wrapper (opencode.json, in-process TS plugin)
.claude-plugin/ Claude Code plugin manifest (canonical for version + description)
plugin.json Root mirror of .claude-plugin/plugin.json (for non-Claude tools)
references/ Cross-skill reference docs (blind-dispatch, model-routing, portability)
scripts/ Deterministic tooling — prefer these over LLM judgment for mechanical work
docs/ projects/ (active + archive), plans/, BACKLOG.md, CHANGELOG.md
.githooks/ Repo-tracked pre-commit hooks (activated via scripts/install-hooks.sh)
Skill body is in skills/<name>/SKILL.md. Methodology agent prompt body is in agents/<role>.md. Hooks live in hooks/ and are registered via hooks/hooks.json.
Coding Conventions (spec)
- Severity vocabulary (unified across skills + agents):
🔴 Critical / 🟠 Major / 🟡 Minor / 🔵 Suggestion. The dialectic skills (think-tank*) use a separate lowercasecritical / important / minortag for risk-not-severity — intentionally distinct. - No hardcoded dispatch metadata in skill files. Use
scripts/resolve-dispatch.shto map role →{model, mode, agent}JSON. - Prefer scripts over LLM judgment for mechanical work (regex scans, JSON parsing, diff filtering). When you write a new script, wire it into both
CLAUDE.mdscripts inventory and the relevant skill's "Available Scripts" table.
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.
- 2d ago First seen · 105 lines · 3,191 tokens per session scan A 5903901a9c22
autopilot AGENTS.md is an instructions file published in the GitHub repository cookys/autopilot (11 stars, last pushed 2d ago), licensed MIT. It adds 3,191 tokens to every session, about $0.0160 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.
Other instructions, from other repositories
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.
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).
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.
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.
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).
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.