Garmin MCP Server is a Model Context Protocol server that connects Garmin Connect to Claude and other compatible clients, allowing them to access fitness and health data. It supports users who want to inspect and manage activities, health metrics, training information, workouts, gear, and related performance data through an MCP client. The catalogue includes one skill and one instruction for working with the server.
Borrowing it
Nothing to install: this file belongs to Taxuspt/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/Taxuspt/garmin_mcp/main/.claude/skills/babysit-prs/SKILL.mdgit clone --depth 1 https://github.com/Taxuspt/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/skills/taxuspt/garmin_mcp/babysit-prs)<a href="https://agentmods.dev/skills/taxuspt/garmin_mcp/babysit-prs"><img src="https://agentmods.dev/badge/skills/taxuspt/garmin_mcp/babysit-prs/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/taxuspt/garmin_mcp/babysit-prs"><img src="https://agentmods.dev/badge/skills/taxuspt/garmin_mcp/babysit-prs.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 | $0.00082 | $0.04813 |
| Opus 5.5 | $0.00033 | $0.01925 |
| Sonnet 5.5 | $0.00016 | $0.00963 |
| Haiku 4.5 | $0.00008 | $0.00481 |
Grade A, and why
babysit-prs 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 15d 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 — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Babysit PRs
Read project.md (next to this file) first. It holds this project's skip
list, stop-and-ask lists, message rules, conventions and test command.
Preview mode: if the arguments contain preview, do steps 1 and 2 only and
run read-only commands only (git remote, git fetch, gh pr list/view/diff/checks,
gh run list, gh issue list/view). Do not check out, push, comment, approve,
merge or close anything, and do not ask for approval. End with: "Preview only,
nothing was changed. Run /babysit-prs to act on this plan." Don't act on any
reply in the same run.
Rules for the whole run
- The contributor keeps the credit. Land outside work through the
contributor's own PR. Re-land only when step 3 says so, and then keep their
commits. Never apply someone's diff with
gh pr diff | git applyand commit it as yourself, and never usegit commit --reset-authoron their commits. - Name the repository on every
ghcommand:-R Taxuspt/garmin_mcp. In a clone with several remotes,ghcan silently pick another one.gh apihas no-R; it takes the repository in the path (repos/Taxuspt/garmin_mcp/...). - Use the right git remote. Run
git remote -vand find the remote whose URL containsTaxuspt/garmin_mcp. This file calls it<up>; write its real name (oftenoriginorupstream) wherever you see<up>. Never use a remote that points at a fork, and never push to<up>'smain. - Merge with GitHub's default message. For a PR a contributor opened:
gh pr merge <PR> -R Taxuspt/garmin_mcp --squash --match-head-commit <sha>. For a re-land PR you opened:--rebaseinstead of--squash(see Re-land). Never pass--bodyor--body-file: the default message carries theCo-authored-by:lines, and a custom body drops them.<sha>is the current head of the PR you are about to merge (for a PR you just opened, that is the new PR):gh pr view <PR> -R Taxuspt/garmin_mcp --json headRefOid --jq .headRefOid. Read it again after any push. - One approval per batch. Change nothing before the maintainer approves the plan in step 2, and do nothing that isn't in the approved plan.
- If a step fails or a PR isn't in the state the plan expected, stop work on
that PR and put it in the report with the error. Don't work around it: no
force-push, no
gh pr merge --admin, no rebasing a contributor's branch, no dropping--match-head-commit. One exception: if a merge fails with "Base branch was modified", ormergeableshowsUNKNOWN, re-readmergeableand<sha>and try once more. - Never close a contributor's PR without a comment that thanks them and
says where their work went. Post it with
gh pr commentbeforegh pr close;gh pr close --commentskips the comment if the PR is already closed. - Leave
.github/workflows/changes to the maintainer. The gh token usually lacks theworkflowscope. Never approve CI runs for, push to, or merge a PR that changes workflow files, Dependabot ones included. Give the click steps from step 3 instead. - No AI attribution. Don't add a
Co-authored-byor "Generated with" line for Claude or any other AI to commits, PR bodies or comments;project.mdforbids it. If Claude Code keeps adding one, the maintainer can set"attribution": {"commit": "", "pr": ""}in Claude Code's settings.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 15d ago Changed · +243 lines · +33 tokens per session 7fa33430d4e0
- 16d ago First seen · 147 lines · 49 tokens per session scan A 4baddbb7111e
babysit-prs is a skill published in the GitHub repository Taxuspt/garmin_mcp (1,424 stars, last pushed 5d ago), licensed MIT. It adds 82 tokens to every session and 4,813 once invoked, about $0.0003 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 2026-10-13.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
hero-diff-highlight
A dark code editor reveals a red deletion then a green addition with a soft pulse. Function: PR / code-change explainer.
git-pr-workflows-git-workflow
Guide changes through code checks, testing, commits, and pull request preparation. Use when coordinating a complete Git workflow and verifying readiness for collaboration.