health-mcp: Instructions file for Codex

AGENTS.md

health-mcp AGENTS.md is an instructions file for Codex, OpenCode from jonathan249/health-mcp. It costs 589 tokens per session, scanned A, original, MIT.

A set of repository instructions for working on a Garmin-related MCP server, including its files, commands, coding rules, and tests.

In plain words
What is it for?
Use it when changing the server, its Garmin API connection, caching, tool handlers, or tests. It also records how to start the server locally.
Why use it?
It tells a coding agent how the project is organized and how to build, run, and test it safely.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is jonathan249/health-mcp's own configuration. It tells Codex and OpenCode how to work on health-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything health-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jonathan249/health-mcp. 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/jonathan249/health-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/jonathan249/health-mcp

Made for: Codex, OpenCode.

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 health-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jonathan249/health-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/jonathan249/health-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jonathan249/health-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jonathan249/health-mcp/agents-md/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.

agentmods 80×15 button for health-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jonathan249/health-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jonathan249/health-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 589 This file is loaded in full into every session.
When invoked 589 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00589 $0.00589
Opus 5.5 $0.00236 $0.00236
Sonnet 5.5 $0.00118 $0.00118
Haiku 4.5 $0.00059 $0.00059

Measured 2mo ago against content hash 9481d8ce0feb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

health-mcp AGENTS.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 2mo 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.

AGENTS.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

server.py is the command-line entry point. It adjusts sys.path before loading the application from mcp/main.py, where the FastMCP server and transport are configured. Garmin API access, authentication, response mapping, and caching live in gateway.py. Tool handlers are registered in mcp/tools.py, while their dataclass response types are defined in mcp/models.py.

Tests live in tests/ and mirror the main boundaries: test_gateway.py covers Garmin mapping and caching, and test_server.py checks tool registration. icon.png is the README asset. Keep mcp/ without an __init__.py; making it a package would shadow FastMCP's third-party mcp dependency.

Build, Test, and Development Commands

Create an isolated environment and install dependencies:

python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

Run all tests with python -m unittest discover -s tests. Start the default stdio server with python server.py; stdin is reserved for MCP JSON-RPC. For local HTTP development, run python server.py --transport http, which exposes http://127.0.0.1:8000/mcp. There is no separate build step or configured lint/format command.

Coding Style & Naming Conventions

Follow existing Python style: four-space indentation, type annotations, from __future__ import annotations, and small single-purpose helpers. Use snake_case for functions and variables, PascalCase for classes and dataclasses, and leading underscores for private helpers. MCP tool names use the get_<metric> pattern. Keep imports grouped as standard library, third-party, then local modules.

Testing Guidelines

Tests use the standard-library unittest framework and should be named test_*.py, with methods beginning test_. Avoid live Garmin calls: inject a fake client or gateway, as current tests do. Add focused tests for response mapping, cache behavior, validation, and registered tool names when changing those areas.

Read the full file on GitHub · 62 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. 2mo ago First seen · 62 lines · 589 tokens per session scan A 9481d8ce0feb

Subscribe to this mod's changes

health-mcp AGENTS.md is an instructions file published in the GitHub repository jonathan249/health-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 589 tokens to every session, about $0.0024 per session on Opus 5.5. 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.

Related

health-mcp AGENTS.md compared with instructions from other repositories

health-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
health-mcp AGENTS.mdjonathan249/health-mcpInstructions file05mo agoMITA589Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot