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/stacklok/toolhive-studio/claude-mdgit clone --depth 1 https://github.com/stacklok/toolhive-studioWhat 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 | $0.01205 | $0.01205 |
| Opus 5 | $0.00602 | $0.00602 |
| Sonnet 5 | $0.00241 | $0.00241 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
toolhive-studio 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 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This file provides guidance to Claude Code when working with this repository.
Project Overview
ToolHive Studio is an Electron desktop application for managing MCP (Model Context Protocol) servers. Built with React, TypeScript, and Vite. The Electron app bundles the ToolHive CLI (thv) binary.
Build and Development Commands
pnpm install # Install dependencies
pnpm run start # Start dev server with hot reload
pnpm run lint # Run ESLint
pnpm run type-check # TypeScript checking (both app and node configs)
pnpm run format # Format with Prettier
pnpm run test:nonInteractive # Run unit tests once
pnpm run test # Run unit tests in watch mode
pnpm run test:coverage # Unit tests with coverage
pnpm run e2e # Package + run Playwright e2e tests
pnpm run knip # Detect unused code
pnpm run generate-client # Fetch OpenAPI spec + regenerate API client
Husky/lint-staged automatically run lint + format on staged .ts/.tsx files. Run pnpm run type-check manually before committing — it is not covered by the hook.
Environment Requirements
- Node.js >=24 <25 (use
nvm use—.nvmrcis present) - pnpm package manager
- Docker daemon must be running (required by ToolHive)
Common Gotchas
- Docker must be running before
pnpm run start— ToolHive manages containers, so the daemon is required even in dev - Node version mismatch: wrong Node version can break other native modules. Always
nvm usefirst - Stale generated types: if type errors reference API types, run
pnpm run generate-clientto refresh - Electron test runner: unit tests run through Electron (
vitest:electron), not plain Node — required for native module compatibility - All commands from root: always run
pnpmcommands from the repository root, not from subdirectories
Auto-Generated Code — Never Edit Manually
These files are generated and will be overwritten:
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 · 104 lines · 1,205 tokens per session scan A 38e28da54acc
toolhive-studio CLAUDE.md is an instructions file published in the GitHub repository stacklok/toolhive-studio (163 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,205 tokens to every session, about $0.0060 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
stride-gpt AGENTS.md
Instructions for mrwadams/stride-gpt, covering agents.md, what this project is, repository layout, how the agentic analysis works and progressive disclosure pattern.
mcp-dotnet-samples AGENTS.md
Instructions for microsoft/mcp-dotnet-samples, covering agents.md - mcp .net samples, project overview, project structure and architecture, repository organization and sample components.
qwed-verification copilot-instructions.md
Instructions for QWED-AI/qwed-verification: Read and follow QWEDRULES.md for every suggestion.
assay CLAUDE.md
Instructions for Rul1an/assay, covering assay - ai agent context, what is assay?, workspace structure, key commands and cli entry points.
examples CLAUDE.md
Claude Code instructions for rossoctl/examples, covering claude.md - agent examples, repository structure, key commands, code style and dco sign-off (mandatory).
Project-Koma AGENTS.md
Instructions for swnotmetal/Project-Koma, covering koma — ai coding agent rules, when to use koma, quick integration, design rules and package overview.