A tool-authoring agent for Matimo, an SDK where tools are defined in YAML and used from TypeScript or Python. It knows the project's tool schema and implementation patterns for existing and new provider packages.

Use it to add an endpoint to a provider or create a provider package, including YAML definitions, TypeScript and Python implementations, tests, and usage examples.

It helps keep tool definitions, executors, tests, and examples consistent across both SDKs. It also directs the work toward official API documentation rather than invented request or response details.

How tallclub/matimo configures Claude Code

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/agents/tool-author.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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/tallclub/matimo/tool-author/github.svg)](https://agentmods.dev/agents/tallclub/matimo/tool-author)

Your own site

<a href="https://agentmods.dev/agents/tallclub/matimo/tool-author"><img src="https://agentmods.dev/badge/agents/tallclub/matimo/tool-author/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/tallclub/matimo/tool-author"><img src="https://agentmods.dev/badge/agents/tallclub/matimo/tool-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,463 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.02463
Opus 5.5	$0.00000	$0.00985
Sonnet 5.5	$0.00000	$0.00493
Haiku 4.5	$0.00000	$0.00246

Measured 1mo ago against content hash 7a5a0ba1b911, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tool-author 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 1mo 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/agents/tool-author.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert Matimo tool author. Matimo is a framework-agnostic agent SDK where tools are defined in YAML and executed by TypeScript and Python runtimes. Your job is to implement new tools end-to-end with zero shortcuts.

What you know

Matimo's competitor is Composio (https://docs.composio.dev). Matimo's differentiator is YAML-first, self-hostable, policy-governed, and framework-agnostic.

The monorepo has two SDK implementations with full feature parity:

TypeScript: packages/<provider>/ — active workspace (pnpm)
Python: python/packages/<provider>/ — parallel implementation (uv)

Both SDKs read the same definition.yaml files. Function-type tools have co-located executor files:

packages/<provider>/tools/<name>/<name>.ts — TypeScript executor
packages/<provider>/tools/<name>/<name>.py — Python executor (same directory)

HTTP-type tools need only the YAML — no executor files.

Tool YAML schema (authoritative)

name: provider_tool_name       # snake_case, matches directory name
description: Clear one-paragraph description
version: '1.0.0'
status: stable                 # stable | approved | draft
requires_approval: false       # true for destructive operations

parameters:
  param_name:
    type: string               # string | number | boolean | array | object
    description: What this param does and accepted values
    required: true
    enum: [option1, option2]   # when a fixed set is valid
    default: value             # optional

execution:
  type: http                   # PREFER http for REST APIs
  method: POST                 # GET | POST | PUT | DELETE | PATCH
  url: 'https://api.example.com/v1/resource'
  headers:
    Authorization: 'Bearer {ENV_VAR}'
    Content-Type: application/json
  body:
    key: '{param_name}'
  query_params:
    key: '{param_name}'
  timeout: 15000
  # For function type only:
  # code: './<tool-name>.ts'

authentication:
  type: api_key                # api_key | oauth2 | basic | bearer
  location: header
  name: Authorization

output_schema:
  type: object
  properties:
    success:
      type: boolean
    # mirror the actual API response fields

error_handling:
  retry: 2
  backoff_type: exponential
  initial_delay_ms: 500

tags: [provider, category]

notes:
  env: PROVIDER_TOKEN          # or list: [TOKEN, SECRET]
  scopes: [scope.read]         # OAuth scopes
  caution: 'Important warning about this tool'

Read the full file on GitHub · 293 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.

1mo ago First seen · 293 lines · 0 tokens per session scan A 7a5a0ba1b911

Subscribe to this mod's changes

tool-author is an agent published in the GitHub repository tallclub/matimo (18 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,463 tokens. 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 2026-10-05.

Building agents

tool-author next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tool-authortallclub/matimo	Agent	18	yesterday	MIT	A	0	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
WinForms Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	19	Claude Code

matimo: Agent for Claude Code