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/metamask/core/agents-mdgit clone --depth 1 https://github.com/MetaMask/coreWhat 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 | $0.03086 | $0.03086 |
| Opus 5 | $0.01543 | $0.01543 |
| Sonnet 5 | $0.00617 | $0.00617 |
| Haiku 4.5 | $0.00309 | $0.00309 |
Grade A, and why
core 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guidelines for AI agents
This document provides guidance for AI agents working within this repo.
Architecture
Stack
- Yarn 4 for managing the monorepo
- TypeScript 5 for writing type-safe code
- Jest for writing tests
- ESLint 9 and Prettier for linting and formatting code
- Babel for compiling ESM code so that Jest can run it
@metamask/auto-changelogfor writing and validating changelogs@metamask/create-release-branch,MetaMask/action-publish-release, andMetaMask/action-npm-publishfor creating and publishing releases- TypeDoc for generating API documentation
Package structure
Yarn workspaces are used to define and manage multiple packages.
Package in this monorepo are represented by subdirectories in packages/. Each directory follows this structure:
src/— Files that get built and published when the package is released. May also contain tests (which do not get published).tests/— Optional directory that defines helpers or setup for tests.package.json— Defines the name of the package, current version, dependencies, etc.CHANGELOG.md— Each package has a changelog that lists historical changes.README.md— Introduces the package to engineers and provides instructions on how to install and use it.LICENSE— Each package has a license that describes how engineers can use it in projects.- Configuration files — See below.
Note that the package template in scripts/create-package/package-template also uses this same structure.
Configuration files
The monorepo uses a hierarchical configuration approach for different tools. For most tools, root-level config files define shared settings, while package-level files extend or customize them.
Contributing teams and codeowners
CODEOWNERSdefines which GitHub teams own which packages in the monorepo.teams.jsoninstructs thecreate-update-issuesGitHub workflow which labels to assign issues that are created when there are new major version releases of packages.
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 · 236 lines · 3,086 tokens per session scan A c91a75d99f36
core AGENTS.md is an instructions file published in the GitHub repository MetaMask/core (413 stars, last pushed 3d ago), licensed MIT. It adds 3,086 tokens to every session, about $0.0154 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
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).
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.
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.