git-commit-message

git-commit-message is a skill for Claude Code, Codex from bkircher/skills. It costs 13 tokens per session (679 once invoked), scanned A, original, MIT.

A helper that writes a Git commit message from changes already selected for commit. It also checks recent commit wording so the message fits the repository.

In plain words
What is it for?
Use it when preparing a commit from staged files and needing a concise message that matches the project's existing style.
Why use it?
It avoids writing a message by hand or accidentally describing changes that were not selected. If nothing is selected, it reports that instead of guessing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when preparing a commit from staged files and needing a concise message that matches the project's existing style.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bkircher/skills/git-commit-message
Install

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.

Any agent
npx skills add bkircher/skills --skill git-commit-message
Clone the repo
git clone --depth 1 https://github.com/bkircher/skills

Made for: Claude Code, Codex.

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 git-commit-message

README.md
[![agentmods](https://agentmods.dev/badge/skills/bkircher/skills/git-commit-message/github.svg)](https://agentmods.dev/skills/bkircher/skills/git-commit-message)
Your own site
<a href="https://agentmods.dev/skills/bkircher/skills/git-commit-message"><img src="https://agentmods.dev/badge/skills/bkircher/skills/git-commit-message/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 git-commit-message

Your own site · 80×15
<a href="https://agentmods.dev/skills/bkircher/skills/git-commit-message"><img src="https://agentmods.dev/badge/skills/bkircher/skills/git-commit-message.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 679 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 $0.00013 $0.00679
Opus 5.5 $0.00005 $0.00272
Sonnet 5.5 $0.00003 $0.00136
Haiku 4.5 $0.00001 $0.00068

Measured 28d ago against content hash ea686b5b4683, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

git-commit-message 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 28d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/validate_commit_message.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

git-commit-message/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a commit message for the staged changes. If changes are staged, return only the commit message, with no code fence or commentary. Otherwise, report that nothing is staged.

Inspect the staged changes

List the staged files:

If this produces no output, report that nothing is staged and do not invent a message. Otherwise, read the complete staged diff:

Use the conversation context to understand the rationale, but describe only the staged diff. Ignore unstaged and untracked changes.

Inspect the repository style

Read recent non-merge commit subjects before drafting the message:

Match the established style. Use Conventional Commit syntax such as feat(scope): ... or fix(scope): ... only when it clearly dominates recent history. Isolated examples and component prefixes such as subdir: ... do not establish that convention.

Use concise, natural language

  • Prefer plain, slightly informal engineering language over formal wording.
  • When unambiguous, prefer infra, config, prod, and dev over infrastructure, configuration, production, and development.
  • Preserve exact names from the staged diff and follow established repository terminology when it differs.

Write the subject

  • Limit the subject to 50 characters.
  • Use the imperative mood: fix, not fixed or fixes.
  • Do not end the subject with a period.
  • When changes affect one clear component and history uses component prefixes, use <component>: <imperative summary> and match the casing used in recent history. Otherwise, capitalize the first word of an unprefixed subject.

Write the body

Use this format unless the subject fully describes one small, self-explanatory change:

<subject>

Changes:
- <change or rationale>
- <change or rationale>
  • Separate the body from the subject with a blank line.
  • Keep every body line within 72 characters, including indentation.
  • Explain what changed and why without repeating the subject or including unnecessary implementation details.
  • Use only as many bullets as needed; do not invent items to reach a fixed count.
  • Do not end a one-line bullet with a period.
  • Wrap bullets at word boundaries and indent continuation lines by two spaces.

Read the full file on GitHub · 104 lines

Files

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.

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. 28d ago Changed · -2 tokens per session ea686b5b4683
  2. 2mo ago First seen · 104 lines · 15 tokens per session scan A 29df2af934f6

Subscribe to this mod's changes

git-commit-message is a skill published in the GitHub repository bkircher/skills (11 stars, last pushed 6d ago), licensed MIT. It adds 13 tokens to every session and 679 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 2026-08-30.