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.
curl -O https://raw.githubusercontent.com/jhoy1020/garmin-coach-mcp/main/.claude/skills/garmin-coach-usage/SKILL.mdgit clone --depth 1 https://github.com/jhoy1020/garmin-coach-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/skills/jhoy1020/garmin-coach-mcp/garmin-coach-usage)<a href="https://agentmods.dev/skills/jhoy1020/garmin-coach-mcp/garmin-coach-usage"><img src="https://agentmods.dev/badge/skills/jhoy1020/garmin-coach-mcp/garmin-coach-usage/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/jhoy1020/garmin-coach-mcp/garmin-coach-usage"><img src="https://agentmods.dev/badge/skills/jhoy1020/garmin-coach-mcp/garmin-coach-usage.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 | $0.00071 | $0.00846 |
| Opus 5 | $0.00036 | $0.00423 |
| Sonnet 5 | $0.00014 | $0.00169 |
| Haiku 4.5 | $0.00007 | $0.00085 |
Grade A, and why
garmin-coach-usage 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using the Garmin tools
Which tool answers what
| Question | Tool |
|---|---|
| "Is this connected?" / "whose account?" | garmin_status |
| "What have I done lately?" | list_activities |
| "Details of that session?" | get_activity |
| "What did I actually lift?" | get_exercise_sets |
| "Is my bench going up?" | get_strength_history |
| "How did I sleep? Am I recovered?" | get_recovery |
| "How is my resting HR trending?" | get_trends |
| "What weight next?" | suggest_next_weight |
| Create / schedule / delete a workout | create_strength_workout, schedule_workout, delete_workout |
Start with garmin_status if anything looks wrong — it distinguishes "not authenticated"
from "no data".
What data actually exists
- Strength history needs sets logged with weights on the watch. If the user recorded a lifting session as a generic "Cardio" or "Other" activity, or logged no weights, these tools correctly return nothing. Say that rather than implying a bug.
- Sleep and body-battery need the watch worn overnight.
- Garmin's API is unofficial. A backend change can break a tool without warning; that is a known, accepted limitation of the project.
Be careful with these
suggest_next_weight is a heuristic, not coaching. It extrapolates from recent
sets. It knows nothing about how the user slept, whether they are injured, or what their
programme is. Present it as a starting point and let them judge.
The three write tools change a real Garmin calendar.
- Confirm before calling them.
create_strength_workoutbuilds Garmin's unofficial workout schema. Always tell the user to open the Garmin Connect app and check it looks right.- Always mention
delete_workoutas the undo, and keep the returnedworkout_idhandy so you can offer it concretely. - If
GARMIN_COACH_READONLYis set they will not be in the tool list at all — that is configuration, not a failure.
Dates and "today"
Tools that resolve "today" use the server's clock. Locally that is the user's
machine. Hosted, it is the container's TZ — which defaults to UTC and will resolve to
tomorrow from late afternoon onward, returning empty results, unless
GARMIN_COACH_TIMEZONE is set. If "today" looks empty in the evening on a hosted
deployment, that is the first thing to check.
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 · 74 lines · 71 tokens per session scan A 5f9949ede53f
garmin-coach-usage is a skill published in the GitHub repository jhoy1020/garmin-coach-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 846 once invoked, about $0.0004 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 skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.