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/eddmann/intervals-icu-mcp/claude-mdgit clone --depth 1 https://github.com/eddmann/intervals-icu-mcpWrote 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/eddmann/intervals-icu-mcp/claude-md)<a href="https://agentmods.dev/instructions/eddmann/intervals-icu-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/eddmann/intervals-icu-mcp/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 | $0.01447 | $0.01447 |
| Opus 5 | $0.00724 | $0.00724 |
| Sonnet 5 | $0.00289 | $0.00289 |
| Haiku 4.5 | $0.00145 | $0.00145 |
Grade A, and why
intervals-icu-mcp 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.
How it starts
The opening of the file, as written. The whole thing — 219 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 Overview
This is an MCP (Model Context Protocol) server for Intervals.icu that provides 40+ tools, 1 resource, and 6 prompts for accessing training data, wellness metrics, and performance analysis through Claude and other LLMs.
Development Commands
Setup & Dependencies
# Install dependencies
make install
# Update dependencies
make update
# Setup authentication
make auth
Testing & Linting
# Run all pre-release checks (same as CI)
make can-release
# Run tests
make test
# Run specific test filter
make test/athlete # runs tests matching "athlete"
# Run tests with verbose output
make test/verbose
# Lint with ruff and pyright
make lint
# Format code
make format
Running Locally
# Run the MCP server
make run
Docker
# Build Docker image
make docker/build
# Run Docker container
make docker/run
Architecture
Core Components
FastMCP Server (server.py)
- Entry point that initializes the FastMCP server
- Registers all tools, resources, and prompts
- Tools are imported from
tools/modules but registered in server.py - Middleware is added before tools are registered
Middleware (middleware.py)
ConfigMiddlewareruns before every tool call- Loads and validates Intervals.icu configuration from environment
- Injects
ICUConfiginto context state viactx.set_state("config", config) - Tools access config via
ctx.get_state("config")
API Client (client.py)
ICUClientis an async HTTP client using httpx- Uses Basic Auth with username "API_KEY" and the API key as password
- All API methods are async and must be used with async context manager
- Handles error responses with
ICUAPIErrorexceptions - Default timeout is 30 seconds
Authentication (auth.py)
ICUConfigloads credentials from.envfile using pydantic-settingsload_config()loads configuration from environmentvalidate_credentials()checks if credentials are properly set- Interactive setup script at
scripts/setup_auth.py
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.
- 6d ago First seen · 219 lines · 1,447 tokens per session scan A 2edd0a599cb6
intervals-icu-mcp CLAUDE.md is an instructions file published in the GitHub repository eddmann/intervals-icu-mcp (35 stars, last pushed 10mo ago), licensed MIT. It adds 1,447 tokens to every session, about $0.0072 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
intervals-icu-mcp CLAUDE.md
Claude Code instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
icuvisor CLAUDE.md
Claude Code instructions for ricardocabral/icuvisor, covering claude.md, what this project is, authoritative documents, hard rules and project layout.
seekstone CLAUDE.md
Claude Code instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
mistral-mcp CLAUDE.md
Instructions for Swih/mistral-mcp, covering claude.md — mistral-mcp, 1. identité du projet, 2. règles dures (ne pas transgresser), 3. layout & responsabilités and 4. conventions de code.
trello-mcp AGENTS.md
AGENTS.md instructions for enthouan/trello-mcp, covering agents.md, project summary, hard constraints, runtime and package manager and common commands.