garmin-connect-mcp: Command for Claude Code

.claude/commands/commit.md

commit is a command for Claude Code from epodivilov/garmin-connect-mcp. It costs 8 tokens per session (2,784 once invoked), scanned A, original, MIT.

A command for creating Git commits, which are saved checkpoints of changes in a code project. It can optionally limit the commit to files matching a path, project, file type, or other description.

In plain words
What is it for?
Use `/commit` to commit all changes, or provide a filter such as a directory, project, documentation, or test files to commit only a selected part of the work.
Why use it?
It reduces the manual work of selecting changed files and preparing a consistent commit message. It also supports skipping pre-commit checks when explicitly requested.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is epodivilov/garmin-connect-mcp's own configuration. It tells Claude Code how to work on garmin-connect-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything garmin-connect-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to epodivilov/garmin-connect-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.

Copy the file
curl -O https://raw.githubusercontent.com/epodivilov/garmin-connect-mcp/main/.claude/commands/commit.md
Clone the repo
git clone --depth 1 https://github.com/epodivilov/garmin-connect-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for commit

README.md
[![agentmods](https://agentmods.dev/badge/commands/epodivilov/garmin-connect-mcp/commit/github.svg)](https://agentmods.dev/commands/epodivilov/garmin-connect-mcp/commit)
Your own site
<a href="https://agentmods.dev/commands/epodivilov/garmin-connect-mcp/commit"><img src="https://agentmods.dev/badge/commands/epodivilov/garmin-connect-mcp/commit/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.

agentmods 80×15 button for commit

Your own site · 80×15
<a href="https://agentmods.dev/commands/epodivilov/garmin-connect-mcp/commit"><img src="https://agentmods.dev/badge/commands/epodivilov/garmin-connect-mcp/commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,784 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00008 $0.02784
Opus 5.5 $0.00003 $0.01114
Sonnet 5.5 $0.00002 $0.00557
Haiku 4.5 $0.00001 $0.00278

Measured 2mo ago against content hash 4aadba1f612a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

commit 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 2mo 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.

.claude/commands/commit.md · 282 lines

How it starts

The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Command: Commit

This command helps you create well-formatted commits with conventional commit messages and emoji. You can optionally provide a filter or context to commit only specific files.

Usage

To create a commit of all changes, just type:

/commit

Or commit only specific files by providing a filter/context:

/commit only src/tools/
/commit изменения для проекта А
/commit только файлы документации
/commit changes in tests

You can also use the --no-verify flag to skip pre-commit checks:

/commit --no-verify
/commit only backend --no-verify

What This Command Does

Filter/Context provided: $ARGUMENTS

  1. Filter Files (if context provided):

    • If $ARGUMENTS is not empty, analyze all modified files using git status
    • Filter files based on the provided context (e.g., directory path, project name, file type)
    • Only stage files that match the filter criteria
    • If $ARGUMENTS contains path patterns (e.g., "src/tools/", "*.test.ts"), use them directly for git add
    • If $ARGUMENTS contains descriptive text (e.g., "проект А", "documentation"), intelligently select matching files
  2. Pre-commit Checks:

    • Unless specified with --no-verify, automatically runs pre-commit checks:
      • pnpm lint to ensure code quality
      • pnpm build to verify the build succeeds
  3. Stage Files:

    • Checks which files are staged with git status
    • If 0 files are staged and no filter provided, automatically adds all modified and new files with git add
    • If filter provided, only adds files matching the filter
  4. Analyze Changes:

    • Performs a git diff to understand what changes are being committed
    • Analyzes the diff to determine if multiple distinct logical changes are present
    • If multiple distinct changes are detected, suggests breaking the commit into multiple smaller commits
  5. Create Commit:

    • For each commit (or the single commit if not split), creates a commit message using emoji conventional commit format
    • Commit message reflects the filtered changes if a filter was applied

Read the full file on GitHub · 282 lines

Changes

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.

  1. 2mo ago First seen · 282 lines · 8 tokens per session scan A 4aadba1f612a

Subscribe to this mod's changes

commit is a command published in the GitHub repository epodivilov/garmin-connect-mcp (8 stars, last pushed 9mo ago), licensed MIT. It adds 8 tokens to every session and 2,784 once invoked, about $0.0000 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 2026-08-31.