Borrowing it
Nothing to install: this file belongs to mskerwiderski/mcp-garmin. 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/mskerwiderski/mcp-garmin/main/CLAUDE.mdgit clone --depth 1 https://github.com/mskerwiderski/mcp-garminWrote 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/mskerwiderski/mcp-garmin/claude-md)<a href="https://agentmods.dev/instructions/mskerwiderski/mcp-garmin/claude-md"><img src="https://agentmods.dev/badge/instructions/mskerwiderski/mcp-garmin/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.
<a href="https://agentmods.dev/instructions/mskerwiderski/mcp-garmin/claude-md"><img src="https://agentmods.dev/badge/instructions/mskerwiderski/mcp-garmin/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00576 | $0.00576 |
| Opus 5.5 | $0.00230 | $0.00230 |
| Sonnet 5.5 | $0.00115 | $0.00115 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
mcp-garmin 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 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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-garmin
Read-only, multi-tenant MCP server for Garmin Connect.
Read docs/architecture.md before changing anything. It carries the design decisions and the Garmin quirks behind them; this file only adds what is specific to working in this repository.
Documentation and code comments are English here, deviating from the portfolio convention, because this repository is written to be handed to other people.
Rules that are easy to break
client.pyandfit/*are vendored from MyFITContainer. Fixes have to be carried to the other repository by hand. Additions here carry amcp-garmin additionmarker.- Every tool needs a projection. Raw Garmin JSON in a response is a bug - see the projection section in the architecture document.
- Every tool needs
_guard. Without it the SDK swallows the cause and the model seesError executing tool <name>. - Never bind a session at registration time.
tools.registertakes a resolver function; an instance would make the server single-tenant. db.conn()skips its commit when an exception passes through. Commit before raising.- Docstrings are user interface. They are what the model reads when deciding which tool to call.
Working on it
python3.12 -m venv .venv && .venv/bin/pip install -e ".[dev]"
.venv/bin/pytest
.venv/bin/ruff check --select E9,F garmin_mcp tests
Tests never touch the network or the real ~/.garmin-mcp; conftest.py points
every path at a temporary directory.
Deployment
Runs on the Strato VPS as /root/mcp-garmin behind
mcp.garmin.skerwiderski.cloud, following the house container pattern: no host
port binding, joins the shared root_default network, Caddy proxies by
container name with flush_interval -1.
Deploy is rsync plus docker compose build && up -d - /root/mcp-garmin is not
a git clone. The .env on the server is never touched from here.
Everything persistent is in the volume at /data. The volume is deliberately
not backed up (it holds other people's Garmin tokens, reissued in minutes);
APP_SECRET belongs in a password manager instead.
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.
- 2mo ago First seen · 55 lines · 576 tokens per session scan A 75d9da02bdd0
mcp-garmin CLAUDE.md is an instructions file published in the GitHub repository mskerwiderski/mcp-garmin (0 stars, last pushed 2mo ago), licensed MIT. It adds 576 tokens to every session, about $0.0023 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.
mcp-garmin CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-garmin CLAUDE.mdmskerwiderski/mcp-garmin | Instructions file | 0 | 2mo ago | MIT | A | 576 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |