garmin-coach-mcp: Instructions file for Claude Code

CLAUDE.md

garmin-coach-mcp CLAUDE.md is an instructions file for Claude Code from jhoy1020/garmin-coach-mcp. It costs 1,673 tokens per session, scanned A, original, MIT.

Repository instructions for an MCP server that exposes one person’s Garmin Connect fitness data to an AI agent. Garmin Connect is Garmin’s online service for storing activity and health data.

In plain words
What is it for?
Use them when working on local or hosted setup, deployment, diagnostics, scripts, or documentation for the Garmin coach server.
Why use it?
They help agents set up, diagnose, deploy, and edit the public repository without exposing passwords, credentials, or the author’s private infrastructure.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; positional $N argument.

This is jhoy1020/garmin-coach-mcp's own configuration. It tells Claude Code how to work on garmin-coach-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 garmin-coach-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jhoy1020/garmin-coach-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/jhoy1020/garmin-coach-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jhoy1020/garmin-coach-mcp

Made for: Claude Code.

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 garmin-coach-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jhoy1020/garmin-coach-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/jhoy1020/garmin-coach-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jhoy1020/garmin-coach-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jhoy1020/garmin-coach-mcp/claude-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 garmin-coach-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jhoy1020/garmin-coach-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jhoy1020/garmin-coach-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,673 This file is loaded in full into every session.
When invoked 1,673 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 $0.01673 $0.01673
Opus 5 $0.00837 $0.00837
Sonnet 5 $0.00335 $0.00335
Haiku 4.5 $0.00167 $0.00167

Measured 10d ago against content hash aecb9f8f6051, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

garmin-coach-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 10d 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.

CLAUDE.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

garmin-coach-mcp — context for agents

An MCP server exposing one person's Garmin Connect data as tools. Runs locally over stdio, or hosted on Azure Container Apps behind Microsoft Entra sign-in.

If someone is setting this up, ask which they want — local takes about two minutes, hosted takes about twenty and costs ~$5/month.

THIS REPOSITORY IS PUBLIC

Read this section before writing to any tracked file.

Never commit any of these. They are not credentials, but they identify the author and are useless to a reader:

  • a path containing a real username — C:\Users\<name>, /home/<name>
  • an absolute path into someone's checkout — derive from repo_root() instead
  • a real resource-group name, an Azure region inside a command, or a Container Apps FQDN
  • a tenant, subscription, client or object GUID
  • an email address, or a real credential expiry date

Use <placeholder> in docs, and derive at runtime in code. python scripts/check_secrets.py enforces this and runs as a pre-commit hook; CI runs it too. A justified exception uses a per-line # check-secrets: allow personal pragma, never a file-wide allowlist.

Secrets live in exactly two places, both gitignored: .azure/<env>/.env and ~/.garminconnect. Nothing else. Do not create a third.

Never print secrets into the conversation. In particular, do not run azd env get-values — it prints three live credentials. Use python scripts/doctor.py, which reports secrets as set/unset, or --connector-url when the URL is actually needed.

Never ask the user for their Garmin password. Hand them the interactive login (python scripts/setup_local.py) and let them type it into their own terminal.

The command is a script

Do not hand the user az or azd incantations to paste. Run the script; if a script cannot do it, extend the script. Prose that drifts from reality is the specific failure this repo already had.

Task Command
Set up locally python scripts/setup_local.py
Diagnose anything python scripts/doctor.py / --remote / --json
Deploy to Azure python scripts/deploy.py
Register the Entra app python scripts/entra_app.py
Upload the Garmin token python scripts/seed_token.py
Rotate a secret python scripts/rotate_secrets.py --help
Get the connector URL python scripts/doctor.py --connector-url
Check before committing python scripts/check_secrets.py

Read the full file on GitHub · 137 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. 10d ago First seen · 137 lines · 1,673 tokens per session scan A aecb9f8f6051

Subscribe to this mod's changes

garmin-coach-mcp CLAUDE.md is an instructions file published in the GitHub repository jhoy1020/garmin-coach-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,673 tokens to every session, about $0.0084 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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens