Borrowing it
Nothing to install: this file belongs to arm/metis. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/arm/metis/main/AGENTS.mdgit clone --depth 1 https://github.com/arm/metisWrote 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.
[](https://agentmods.dev/instructions/arm/metis/agents-md)<a href="https://agentmods.dev/instructions/arm/metis/agents-md"><img src="https://agentmods.dev/badge/instructions/arm/metis/agents-md/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.
<a href="https://agentmods.dev/instructions/arm/metis/agents-md"><img src="https://agentmods.dev/badge/instructions/arm/metis/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01578 | $0.01578 |
| Opus 5 | $0.00789 | $0.00789 |
| Sonnet 5 | $0.00316 | $0.00316 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade A, and why
metis 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 4d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repository-wide rules for coding agents; human contributors start with CONTRIBUTION.md. Metis is a Python 3.12+ security-review CLI built around a typed execution graph.
Working rules
- Read the owning code, callers, focused tests, and routed guide before editing. Search for existing contracts and fix shared behavior once at its owner.
- Keep changes focused; do not add speculative abstractions or compatibility layers. Preserve published imports, entry points, configuration keys, YAML names, ports, and types unless intentionally making a versioned breaking change; external callers need not appear in this repository.
- Update the relevant README, guide, and examples in the same change whenever user-visible behavior, configuration, CLI, output formats, extension contracts, or supported features change. Update this router when an owner moves.
MetisEngineowns composition and lifecycle; stages own typed workflow boundaries; nodes own selectable behavior. Generic graph code must not name built-in-specific nodes; terminalresultis a shared graph convention.- Treat model, tool, extension, repository/file, network, subprocess, SARIF, and persisted-data results as untrusted. When adding or changing a boundary, validate and bound data before it controls paths, commands, persistence, or publication.
- Durable Metis-owned replacement and migration must validate first and preserve the prior readable state on failure.
- Use engine-owned scheduling, cancellation, and cleanup for graph work.
Propagate
concurrent.futures.CancelledError, use finite network/subprocess timeouts, and drain or join owned work before returning. - Preserve unrelated worktree changes. Do not discard, stash, broadly reformat, stage, commit, amend, or force-add ignored output unless the user asks.
- Keep tests and examples offline and credential-free. Installed extensions run inside the Metis process; installation and selection are trust decisions.
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.
- 4d ago First seen · 96 lines · 1,578 tokens per session scan A b878e4b486d5
metis AGENTS.md is an instructions file published in the GitHub repository arm/metis (862 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,578 tokens to every session, about $0.0079 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 2026-09-08.
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).