Borrowing it
Nothing to install: this file belongs to jsaedtler/cookidoo-mcp-docker. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jsaedtler/cookidoo-mcp-docker/main/CLAUDE.mdgit clone --depth 1 https://github.com/jsaedtler/cookidoo-mcp-dockerWrote 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.
[](https://agentmods.dev/instructions/jsaedtler/cookidoo-mcp-docker/claude-md)<a href="https://agentmods.dev/instructions/jsaedtler/cookidoo-mcp-docker/claude-md"><img src="https://agentmods.dev/badge/instructions/jsaedtler/cookidoo-mcp-docker/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01311 | $0.01311 |
| Opus 5 | $0.00656 | $0.00656 |
| Sonnet 5 | $0.00262 | $0.00262 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade A, and why
cookidoo-mcp-docker 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 7d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project
MCP server (Python, FastMCP v3) that lets LLM sessions upload recipes as Cookidoo custom recipes for a Thermomix (TM7 by default), plus tools for recipe details, shopping list, and meal plan. The German authoring guide ships with the server (tool docstrings, MCP prompt, resource, server instructions), so clients need no recipe rules in their own prompts. The project is live: a home-server deployment serves claude.ai connectors through a Cloudflare Tunnel with GitHub OAuth. docs/plan-mcp-server-v1.md is the running decision log - keep it updated when working on features.
Commands
uv sync- install dependencies (Python 3.12+, uv-managed)uv run pytest- full test suite; e2e tests auto-skip without real credentials in.envuv run pytest tests/test_models.py -q- single test fileuv run pytest -m e2e- end-to-end tests against the live Cookidoo API (needs.env; uploads a test recipe and deletes it again)uv run ruff check src tests- lintuv run cookidoo-mcp- run the server (streamable HTTP on 127.0.0.1:8000/mcp;MCP_TRANSPORT=stdiofor stdio)docker compose up -d --build- local container build and run- CI (
.github/workflows/docker.yml) runs ruff + pytest and publishes a multi-arch image toghcr.io/jsaedtler/cookidoo-mcp-docker:lateston every push to main
Architecture
All code lives in src/cookidoo_mcp/; each module has one job:
models.py- pydantic models converting an LLM-authored recipe into the exact Cookidoo PATCH payload. The LLM supplies semantics only (step text, time_seconds, temperature, speed, reverse); the server renders the German settings notation ("3 Min./120°C/Linkslauf/Stufe 1") and computes TTS/INGREDIENT annotation character offsets itself. Never let a model produce offsets or notation text.cookidoo_client.py- the only Cookidoo coupling point. Login/read/delete/shopping list/calendar go through the releasedcookidoo-apilibrary; creating and listing custom recipes use raw POST+PATCH/GET on the undocumentedcreated-recipes/{language}endpoints (reusing the library session and bearer token), because the released library cannot create recipes from scratch. When upstream ships create/list (see miaucl/cookidoo-api PR #179), only this adapter changes.guidance.py- German authoring rules (RECIPE_GUIDE, SERVER_INSTRUCTIONS).auth.py- optional GitHub OAuth (FastMCP GitHubProvider, active only when GITHUB_CLIENT_ID is set) plus a mandatory allowlist middleware: the provider alone would accept any GitHub account. OAuth state persists in a file store under MCP_STATE_DIR; storage keys are hashed because CIMD client IDs are URLs and raw slashes break file paths.server.py- FastMCP wiring (11 tools, prompt, resource), lazy Cookidoo login with re-login on auth expiry, and explicit dual-stack socket binding (asyncio forces IPV6_V6ONLY, which would silently black-hole IPv4 behind Docker ip6tables DNAT).
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.
- 7d ago First seen · 50 lines · 1,311 tokens per session scan A 92e5d6247be3
cookidoo-mcp-docker CLAUDE.md is an instructions file published in the GitHub repository jsaedtler/cookidoo-mcp-docker (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,311 tokens to every session, about $0.0066 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.