Borrowing it
Nothing to install: this file belongs to MECoban/garmin-ai-coach. 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/MECoban/garmin-ai-coach/master/AGENTS.mdgit clone --depth 1 https://github.com/MECoban/garmin-ai-coachWrote 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/mecoban/garmin-ai-coach/agents-md)<a href="https://agentmods.dev/instructions/mecoban/garmin-ai-coach/agents-md"><img src="https://agentmods.dev/badge/instructions/mecoban/garmin-ai-coach/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.
<a href="https://agentmods.dev/instructions/mecoban/garmin-ai-coach/agents-md"><img src="https://agentmods.dev/badge/instructions/mecoban/garmin-ai-coach/agents-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 | $0.00466 | $0.00466 |
| Opus 5 | $0.00233 | $0.00233 |
| Sonnet 5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
garmin-ai-coach 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 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.
What it actually says
AGENTS.md — for AI agents working with this repo
This repository is a Claude Code plugin + skill for Garmin Connect data
access and AI coaching. If you are an AI agent (Claude Code, Cursor, Codex, or
any agent that reads AGENTS.md), this file tells you how to use it.
Use this when
The user wants to: pull / sync / analyze their Garmin Connect data (sleep, resting HR, HRV, body battery, stress, steps, calories, training readiness, VO2max, runs/rides with pace·HR·cadence); build a Garmin-based coach or dashboard; or is stuck authenticating to Garmin from code (429 / 401 / Cloudflare "Verify you are human" / MFA loops).
The one thing that matters: authentication
Since March 2026 Garmin's SSO is behind Cloudflare, which breaks plain
clients and default garth. The working recipe:
import cloudscraper
from garminconnect import Garmin # pin: garminconnect==0.2.38 (garth-based)
client = Garmin(email, password) # Garmin 2FA must be OFF
client.garth.sess = cloudscraper.create_scraper() # ← bypass Cloudflare
client.login()
client.garth.dump("~/.garminconnect") # token cached ~1 year
Inject cloudscraper for data calls too (connectapi.garmin.com is also behind
Cloudflare). Prerequisite: the user's Two-Step Verification must be OFF.
Where to look
- Full executable recipe:
skills/garmin-connect/SKILL.md - Auth script:
scripts/login_garmin.py - Daily sync:
scripts/daily_sync.py - AI coaching push (scheduled cloud agents):
ROUTINES.md
Boundaries
Personal use of the user's OWN data. Not affiliated with Garmin. Activity data contains GPS home location — keep exports private. Not medical advice.
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 · 38 lines · 466 tokens per session scan A a3f4613e98bb
garmin-ai-coach AGENTS.md is an instructions file published in the GitHub repository MECoban/garmin-ai-coach (1 stars, last pushed 2mo ago), licensed MIT. It adds 466 tokens to every session, about $0.0023 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.