Borrowing it
Nothing to install: this file belongs to elias-ramzi/ClaudeCyclingMCP. 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/elias-ramzi/ClaudeCyclingMCP/main/.claude/skills/garmin-upload/SKILL.mdgit clone --depth 1 https://github.com/elias-ramzi/ClaudeCyclingMCPWrote 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/elias-ramzi/claudecyclingmcp/garmin-upload)<a href="https://agentmods.dev/skills/elias-ramzi/claudecyclingmcp/garmin-upload"><img src="https://agentmods.dev/badge/skills/elias-ramzi/claudecyclingmcp/garmin-upload/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/elias-ramzi/claudecyclingmcp/garmin-upload"><img src="https://agentmods.dev/badge/skills/elias-ramzi/claudecyclingmcp/garmin-upload.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 | $0.00132 | $0.02256 |
| Opus 5 | $0.00066 | $0.01128 |
| Sonnet 5 | $0.00026 | $0.00451 |
| Haiku 4.5 | $0.00013 | $0.00226 |
Grade A, and why
garmin-upload 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 11d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Uploading a cycling workout to Garmin Connect
Render the session with the ClaudeCyclingMCP server, upload it with the Garmin MCP, then verify it by fetching it back. A workout that uploads without error can still be stored wrong, and nothing tells you when that happens.
What you need first
- FTP. Never assume one. Unless the athlete states it in the request —
a stated figure beats a profile field and needs no second opinion — call
get_cycling_ftp. It returns anis_staleflag; if stale, say so and confirm the figure with the athlete before rendering. Everything downstream is wrong if the FTP is wrong. - The session itself. If any of duration, intensity or structure is ambiguous, ask before rendering rather than guessing.
Steps
0. Check the destination exists
Confirm the Garmin MCP is connected — you need upload_workout,
get_workout_by_id and delete_workout. If they are not there, say so now,
before rendering. The workout can still be rendered and written to disk for
manual import, but do not begin the upload procedure and do not describe the
result as uploaded.
This costs one look and converts a failure at step 4 into a fact stated at the start. Observed: a full session spent building a workout for a Garmin MCP that was not connected.
1. Write the spec
Call spec_schema if the format isn't already familiar. Keep the spec flat and
readable — someone should be able to see the session in it.
2. Check it before rendering
Call describe_spec. Show the block table to the user. It gives computed
watts, total duration, IF and TSS. This is where a wrong number is cheap to
catch; after upload it is not.
If validate_spec reports warnings, surface them — they usually mean a typo'd
key was silently ignored.
3. Render
Call render_garmin. Always pass out_path — for example
~/workouts/<name>.garmin.json. Not "for example, if convenient": without it
there is no artifact to re-upload, diff, or fall back to, and you will only
discover you wanted one after something has gone wrong.
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.
- 11d ago First seen · 192 lines · 132 tokens per session scan A 2e70336b2508
garmin-upload is a skill published in the GitHub repository elias-ramzi/ClaudeCyclingMCP (0 stars, last pushed 18d ago), licensed MIT. It adds 132 tokens to every session and 2,256 once invoked, about $0.0007 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.