Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add chenhunghan/garmin-mcp-app --skill garmingit clone --depth 1 https://github.com/chenhunghan/garmin-mcp-appWrote 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/skills/chenhunghan/garmin-mcp-app/garmin)<a href="https://agentmods.dev/skills/chenhunghan/garmin-mcp-app/garmin"><img src="https://agentmods.dev/badge/skills/chenhunghan/garmin-mcp-app/garmin/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/skills/chenhunghan/garmin-mcp-app/garmin"><img src="https://agentmods.dev/badge/skills/chenhunghan/garmin-mcp-app/garmin.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 | $0.00035 | $0.00360 |
| Opus 5.5 | $0.00014 | $0.00144 |
| Sonnet 5.5 | $0.00007 | $0.00072 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
garmin 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 12d 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
Run Coach (Garmin data)
Prefer the tools that open a view, and let the view carry the numbers — answer with what they mean, not a list of values:
- "How am I today?", "should I train today?", "morning briefing" →
get-daily-briefing(date optional), then give 2–3 concrete suggestions grounded in the numbers and one thing to watch. - Trends, progress, "is my fitness improving?" →
show-performance-dashboard(metrics and range optional). Compare the current level with the period average, not first vs last day. - Planning a week →
get-training-context, ask for the goal and availability, propose a plan and wait for confirmation, thencreate-structured-workoutfor each session (withscheduleDate) and finish withshow-training-week. - A specific run →
get-activities/get-activities-by-dateto find it, thenget-activity-splits(per-km splits even for single-lap runs) orget-activity-hr-zones. - A saved workout by name →
list-workoutswithname, thenget-workout. - For several days of sleep, stress or heart rate, make ONE call with
dateandendDate(each call opens its own view).
If the user isn't signed in, call garmin-check-auth: it opens the sign-in form in the app (email, password, MFA code). Never ask for the password in the chat.
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.
- 12d ago First seen · 18 lines · 35 tokens per session scan A 49eac447b980
garmin is a skill published in the GitHub repository chenhunghan/garmin-mcp-app (14 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 360 once invoked, about $0.0001 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 2026-10-05.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
grounded-citations
Ground answers and documents in cited, verifiable sources.
baoyu-article-illustrator
Article illustrations: type × style × palette consistency.
flash-attention
Speed up long-sequence transformer training and inference.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
openhands
Delegate coding to OpenHands CLI (model-agnostic, LiteLLM).