Borrowing it
Nothing to install: this file belongs to Sinfjell/garmin-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.
curl -O https://raw.githubusercontent.com/Sinfjell/garmin-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/Sinfjell/garmin-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/sinfjell/garmin-mcp/claude-md)<a href="https://agentmods.dev/instructions/sinfjell/garmin-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sinfjell/garmin-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.
<a href="https://agentmods.dev/instructions/sinfjell/garmin-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sinfjell/garmin-mcp/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 | $0.00623 | $0.00623 |
| Opus 5 | $0.00311 | $0.00311 |
| Sonnet 5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
garmin-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 9d 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.
garmin-mcp
MCP server exposing one person's Garmin Connect data to AI clients, plus multi-tenant hosting and a self-service onboarding app.
Invariants
Break one of these and someone loses access to their data, or gains access to
someone else's. Any diff touching them needs review-against-plan before merge.
-
The running production connector must not break.
garmin-mcp.serviceon the Hetzner host, and the URL it serves, belong to Sindre's own instance. Multi-tenant and onboarding run as separate units on separate ports. Any change that touches the single-tenant code path — including the default--path, the default token store, or existing tool behaviour — has to be proved inert with a before/after MCPinitializecall against the live URL. -
A request may only read the token store its URL names. Tenant isolation rests on the token store bound per request.
get_client()fails closed in multi-tenant mode: no bound store means an error, never a fall back to the host's session or toGARMIN_EMAIL/GARMIN_PASSWORD. Prove isolation by driving the ASGI app over HTTP for two user IDs, not by unit-testing the resolver. -
User IDs are the whole authentication story. Possession-of-URL: 32–128 chars of
[a-z0-9-], generated with ≥128 bits of entropy. Unknown and malformed IDs must return the same 404, so probing reveals nothing. -
A password must never reach disk or a log. It exists for the duration of one Garmin login call and is cleared immediately after — including before the MFA wait. Never log an exception's message or
exc_infoon a login path: a failing HTTP client can echo the request body back, and the request carried the password. Log the exception type. -
Dependencies carry an upper bound. No lockfile exists and the production host re-resolves on restart, so an unpinned dependency means any restart can pull a breaking major. Lift a ceiling only together with a port to the new API — never to make CI green.
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.
- 9d ago First seen · 55 lines · 623 tokens per session scan A 09e68ccdb1eb
garmin-mcp CLAUDE.md is an instructions file published in the GitHub repository Sinfjell/garmin-mcp (0 stars, last pushed 18d ago), licensed MIT. It adds 623 tokens to every session, about $0.0031 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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.