matimo: Instructions file for Claude Code

CLAUDE.md

matimo CLAUDE.md is an instructions file for Claude Code from tallclub/matimo. It costs 4,393 tokens per session, scanned A, original, MIT.

A project instruction file for Matimo, an open-source SDK that lets AI agents use tools through policy checks before those tools run.

In plain words
What is it for?
Use it when modifying Matimo's provider packages, command-line tools, documentation, or its TypeScript and Python implementations.
Why use it?
It explains the project's purpose, layout, commands, and conventions so development work follows the repository's TypeScript and Python structure.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is tallclub/matimo's own configuration. It tells Claude Code 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/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/tallclub/matimo

Made for: Claude Code.

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 CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tallclub/matimo/claude-md"><img src="https://agentmods.dev/badge/instructions/tallclub/matimo/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,393 This file is loaded in full into every session.
When invoked 4,393 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.04393 $0.04393
Opus 5.5 $0.01757 $0.01757
Sonnet 5.5 $0.00879 $0.00879
Haiku 4.5 $0.00439 $0.00439

Measured 6d ago against content hash fa9494ddce3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

matimo 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 6d 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.

CLAUDE.md · 361 lines

How it starts

The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Matimo — CLAUDE.md

Framework-agnostic, policy-governed tool-execution SDK for AI agents. Define a tool once in YAML and deploy it to LangChain, CrewAI, MCP, OpenAI, and Claude. MIT licensed, dual TypeScript + Python implementation at feature parity. Competitor: Composio. A separate hosted product, Matimo Workbench, builds on top of this governance layer with a visual builder — out of scope for this repo.

Package manager: pnpm 8.15.0 | Node: ≥18 | Python: 3.11

What this is

Governance-first: every tool call (built-in, third-party, or agent-created) passes through a policy engine (risk classification low/medium/high/critical, deterministic security rules, HITL quarantine) before executing. On top of that: 129 tools across 10 provider packages (plus a governed Composio catalog for third-party reach), 15 meta-tools for runtime self-extension (matimo_create_tool, matimo_create_skill, matimo_reload_tools, and 12 more), and one YAML tool definition that runs across TS, Python, LangChain, CrewAI, and MCP.


Workspace structure

Root packages/ and root examples/ are dead leftovers — do not add files there. The TypeScript SDK was restructured into typescript/ (commit dfefb3c, "restructure monorepo into typescript/python directories"). Verified directly: git ls-files packages/ and git ls-files examples/ both return 0 — nothing under either root directory is git-tracked. What's physically on disk there (dist/, node_modules/, tsconfig.tsbuildinfo) is stale local build output from before the restructure. There is no pnpm-workspace.yaml at repo root and root package.json is only a 3-line devDependency shim (commitlint, husky). The active TS workspace config is typescript/pnpm-workspace.yaml; run all pnpm commands from typescript/, not repo root. Real examples live in typescript/examples/ and python/examples/.

typescript/                   # THE active pnpm workspace — TypeScript SDK
  pnpm-workspace.yaml         # Authoritative list of active packages
  packages/
    core/
      src/                    # TypeScript source (approval, auth, core, executors, mcp, policy…)
      tools/                  # Built-in YAML tools (calculator, read, web, matimo_* meta-tools)
      skills/                 # Core Matimo SKILL.md files (tool-creation, policy-validation…)
      test/                   # Jest unit + integration tests
    cli/                      # matimo CLI — src/, test/
    slack/                    # Slack tools — tools/, skills/, test/
    gmail/                    # Gmail tools — tools/, skills/, test/
    github/                   # GitHub tools — tools/, skills/
    hubspot/                  # HubSpot tools — tools/, skills/, test/
    notion/                   # Notion tools — tools/, skills/, test/
    postgres/                 # SQL tools — tools/, skills/, test/
    twilio/                   # Twilio SMS/MMS — tools/, skills/, test/
    mailchimp/                # Mailchimp tools — tools/, skills/, test/
    microsoft/                # Microsoft tools
    composio/                 # Composio-routed third-party tools (never call it a "proxy" — see wording note below)
    bruno/                    # WIP package
  examples/
    tools/                    # Per-provider: factory, decorator, langchain, with-approval
    mcp/                      # MCP server examples
python/                       # Python SDK — full feature parity with typescript/
  pyproject.toml              # uv workspace root
  packages/                   # Python package source (uv workspaces), mirrors typescript/packages/ 1:1
  examples/
    native/                   # Direct SDK — mirrors TS factory pattern
    langchain/                # LangChain agents (Python)
    crewai/                   # CrewAI agents
    mcp/                      # MCP server usage (own uv lockfile — separate uv project)
docs/                         # Full docs site: getting-started, api-reference, architecture, tool-development, framework-integrations, mcp, skills
packages/                     # DEAD — untracked leftover build output, not a workspace. Do not add files here.
examples/                     # DEAD — untracked leftover, not a workspace. Do not add files here.

Read the full file on GitHub · 361 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. 6d ago Changed · +19 lines · +527 tokens per session fa9494ddce3d
  2. 23d ago Changed · +2 tokens per session 04dd6387b6cc
  3. 1mo ago Changed · +276 lines · +2,991 tokens per session 52affd5e5dde
  4. 2mo ago First seen · 66 lines · 873 tokens per session scan A 86debfc63edd

Subscribe to this mod's changes

matimo CLAUDE.md is an instructions file published in the GitHub repository tallclub/matimo (18 stars, last pushed yesterday), licensed MIT. It adds 4,393 tokens to every session, about $0.0176 per session on Opus 5.5. 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

matimo CLAUDE.md compared with instructions from other repositories

matimo CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
matimo CLAUDE.mdtallclub/matimoInstructions file18yesterdayMITA4,393Claude Code
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