tool-creation

tool-creation is a skill for Claude Code, Codex from tallclub/matimo. It costs 38 tokens per session (8,032 once invoked), scanned A, original, MIT.

A guide for creating tools for the Matimo SDK, a framework where tool definitions are written in YAML and then executed through the SDK. It covers tool types, authentication, parameters, validation, and approval steps.

In plain words
What is it for?
Use it to define new Matimo tools, choose how they execute, validate their configuration, and add or approve them through the appropriate workflow.
Why use it?
It helps developers follow the SDK’s expected structure and checks instead of creating tools that cannot be loaded or run correctly. It also distinguishes tools created at runtime from tools added to the SDK codebase.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Install

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.

agentmods
npx agentmods add skills/tallclub/matimo/tool-creation
Any agent
npx skills add tallclub/matimo --skill tool-creation
Clone the repo
git clone --depth 1 https://github.com/tallclub/matimo

Made for: Claude Code, Codex.

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 tool-creation

README.md
[![agentmods](https://agentmods.dev/badge/skills/tallclub/matimo/tool-creation.svg)](https://agentmods.dev/skills/tallclub/matimo/tool-creation)
Your own site
<a href="https://agentmods.dev/skills/tallclub/matimo/tool-creation"><img src="https://agentmods.dev/badge/skills/tallclub/matimo/tool-creation.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,032 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00038 $0.08032
Opus 5 $0.00019 $0.04016
Sonnet 5 $0.00008 $0.01606
Haiku 4.5 $0.00004 $0.00803

Measured 6d ago against content hash b7c13c0150bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tool-creation scanned grade A 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

const response = await fetch(url);
typescript/packages/core/skills/tool-creation/SKILL.md · 1,172 lines

How it starts

The opening of the file, as written. The whole thing — 1,172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tool Creation for Matimo SDK

This skill teaches you how to properly create, configure, and validate tools for the Matimo SDK—a configuration-driven framework where tools are defined once in YAML and executed everywhere (factory pattern, decorators, LangChain).

Two audiences — know which one you are:

You are an Agent at runtime You are an SDK developer
Creating tools dynamically via matimo_create_tool Adding tools to the SDK codebase
Tools go to ./matimo-tools/{tool-name}/definition.yaml (configured by developer) Tools go to packages/{provider}/tools/{tool-name}/definition.yaml
Validate with matimo_doctor (meta-tool) Validate with pnpm validate-tools (CLI)
Approval needed: matimo_approve_toolmatimo_reload_tools No approval flow — merged via git

If you are an agent using meta-tools, follow the "Agent at runtime" column throughout this skill.

Matimo Architecture Overview

Tool Execution Flow

Tool Definition (YAML)
         ↓
    ToolLoader (parse & validate)
         ↓
    ToolRegistry (in-memory store)
         ↓
MatimoInstance.execute(name, params)
         ↓
  Select Executor Based on execution.type
         ↓
CommandExecutor | HttpExecutor | FunctionExecutor
         ↓
  Validate output against output_schema
         ↓
    Return structured result

Key Concepts

  • Tools are YAML-first: Define once in YAML, execute anywhere
  • Always include requires_approval: true: Required by policy for all agent-created tools
  • Default execution type is http: command and function types are blocked by policy by default — only use http unless the developer has explicitly enabled the others
  • Parameter templating: Use {paramName} syntax for dynamic values
  • Authentication: Provider-agnostic (API key, bearer, basic, OAuth2)
  • Output validation: All responses validated against Zod schemas
  • Error handling: Structured errors with retry/backoff policies

Read the full file on GitHub · 1,172 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 First seen · 1,172 lines · 38 tokens per session scan A b7c13c0150bb

Subscribe to this mod's changes

tool-creation is a skill published in the GitHub repository tallclub/matimo (11 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 8,032 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens