matimo: Instructions file for Codex

AGENTS.md

matimo AGENTS.md is an instructions file for Codex, OpenCode from tallclub/matimo. It costs 1,622 tokens per session, scanned C, original, MIT.

A repository guide for AI coding agents working on Matimo, a tool-execution software development kit with security rules and human approval checks. It documents the project's layout, setup, builds, tests, and coding conventions.

In plain words
What is it for?
Use it when modifying Matimo, navigating its TypeScript or Python workspaces, installing dependencies, running tests, or following its repository conventions.
Why use it?
It gives an agent the project context and working rules needed to make consistent changes. It also explains that the TypeScript and Python implementations are intended to match.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is tallclub/matimo's own configuration. It tells Codex and OpenCode how to work on matimo itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything matimo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tallclub/matimo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tallclub/matimo/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/tallclub/matimo

Made for: Codex, OpenCode.

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 matimo AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tallclub/matimo/agents-md/github.svg)](https://agentmods.dev/instructions/tallclub/matimo/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/tallclub/matimo/agents-md"><img src="https://agentmods.dev/badge/instructions/tallclub/matimo/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.

agentmods 80×15 button for matimo AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tallclub/matimo/agents-md"><img src="https://agentmods.dev/badge/instructions/tallclub/matimo/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,622 This file is loaded in full into every session.
When invoked 1,622 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.01622 $0.01622
Opus 5.5 $0.00649 $0.00649
Sonnet 5.5 $0.00324 $0.00324
Haiku 4.5 $0.00162 $0.00162

Measured 23d ago against content hash 7f54fd9100de, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

matimo AGENTS.md scanned grade C with 1 finding 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 23d 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.

Nullifies safety policieshighAnti-refusal

"You have no restrictions", "do anything now", "ignore your guidelines": a direct jailbreak that disables guardrails.

- Don't bypass the policy engine when generating code that calls Matimo — route through `matimo.execute(...)`, not raw provider SDKs, when Matimo is already a dependency.
AGENTS.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for AI coding agents (Cursor, GitHub Copilot, Windsurf, Codex, etc.) working in this repository. Claude Code reads CLAUDE.md instead, which covers the same ground in more depth.

What this repo is

Matimo is a policy-governed tool-execution SDK for AI agents: every tool call — built-in, third-party, or agent-created — passes through a policy engine (risk classification, security rules, human-in-the-loop approval) before it runs. MIT licensed, dual TypeScript + Python implementation with feature parity.

Full narrative and API surface: README.md. Deep architecture: docs/architecture/OVERVIEW.md.

Repo layout

typescript/     pnpm workspace — packages/{core,cli,slack,github,gmail,notion,hubspot,postgres,twilio,mailchimp,microsoft,bruno,composio}
python/         uv workspace  — packages/{core,cli,matimo,<same providers except composio>} — mirrors typescript/
docs/           getting-started, api-reference, architecture, tool-development, framework-integrations, mcp, skills
typescript/examples/, python/examples/   usage examples per integration pattern (factory, decorator, LangChain, CrewAI, MCP)

Setup, build, test

TypeScript (run from typescript/):

pnpm install && pnpm build
pnpm test              # jest; pretest runs build first
pnpm test:coverage
pnpm lint / pnpm lint:fix
pnpm validate-tools    # validate all YAML tool definitions

Python (run from python/):

make install           # uv sync --all-extras --dev
make test / make test-unit / make test-integration / make test-coverage
make lint / make format / make typecheck
make validate-tools

Never run npm install inside typescript/ (it uses pnpm-lock.yaml) or pnpm/npm inside python/ (it uses uv/uv.lock) — don't cross-contaminate package managers.

Conventions an agent must follow

  • Conventional Commits, lower-case type: feat, fix, docs, style, refactor, perf, test, chore, ci, revert, example. Enforced by a commitlint pre-commit hook (husky) — don't bypass with --no-verify.
  • TypeScript: strict mode, ESM ("type": "module"), Node ≥22.19, pnpm ≥8.
  • Python: version pinned in python/.python-version; ruff for lint/format; mypy strict on packages/core/src.
  • Every tool (built-in or agent-created) needs an explicit risk classification (low/medium/high/critical) in its YAML definition — see docs/api-reference/POLICY_AND_LIFECYCLE.md.
  • New provider package → mirror an existing one exactly (slack or github are the reference implementations) in both languages. Don't let TS and Python drift — ship new features to both unless told otherwise.
  • 4,400+ tests, 95%+ coverage target across TS + Python — don't drop coverage on new code.
  • Don't hand-edit pnpm-lock.yaml / uv.lock — regenerate via the package manager.

Read the full file on GitHub · 117 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. 23d ago Changed · +2 tokens per session 7f54fd9100de
  2. 1mo ago Changed · +31 tokens per session 20f731dddec7
  3. 2mo ago First seen · 117 lines · 1,589 tokens per session scan C 620fff40156a

Subscribe to this mod's changes

matimo AGENTS.md is an instructions file published in the GitHub repository tallclub/matimo (18 stars, last pushed yesterday), licensed MIT. It adds 1,622 tokens to every session, about $0.0065 per session on Opus 5.5. A static security scan graded it C with 1 finding (nullifies safety policies). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

matimo AGENTS.md compared with instructions from other repositories

matimo AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
matimo AGENTS.mdtallclub/matimoInstructions file18yesterdayMITC1,622Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode