git-commit

A workflow that examines staged Git changes and writes a conventional commit message describing them. Git is a system for tracking changes to code, and a commit records a set of changes.

In plain words
What is it for?
Use it after staging changes to inspect the diff, categorise the work as a feature, fix, documentation change, refactor, or similar type, and create an appropriate commit message.
Why use it?
It saves time when writing commit messages and makes the project history clearer and easier to scan.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/richardcb/oh-my-gemini/git-commit
Any agent
npx skills add richardcb/oh-my-gemini --skill git-commit
Clone the repo
git clone --depth 1 https://github.com/richardcb/oh-my-gemini

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,131 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00043 $0.01131
Opus 5 $0.00022 $0.00566
Sonnet 5 $0.00009 $0.00226
Haiku 4.5 $0.00004 $0.00113

Measured 2d ago against content hash a744556a6f86, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-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 2d 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.

skills/git-commit/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Commit Skill

Goal

Generate meaningful, conventional commit messages by analyzing staged changes. Creates commits that tell a story and make git history useful.

Activation Triggers

  • User says "commit", "git commit", or "save changes"
  • User asks for a commit message
  • After completing implementation tasks

Process

1. Check Git Status

# Check if in a git repo
git rev-parse --git-dir 2>/dev/null || echo "NOT_A_GIT_REPO"

# Check staged changes
git diff --cached --stat

# Check unstaged changes
git status --short

2. Analyze Staged Changes

# Get detailed diff of staged changes
git diff --cached

# Get list of files changed
git diff --cached --name-only

# Get change statistics
git diff --cached --shortstat

3. Categorize Changes

Determine the commit type based on changes:

Type Description Examples
feat New feature New endpoint, new component, new capability
fix Bug fix Error handling, logic correction
docs Documentation README, comments, JSDoc
style Formatting Whitespace, semicolons, no logic change
refactor Code restructuring Rename, extract function, no behavior change
perf Performance Optimization, caching
test Tests New tests, test fixes
chore Maintenance Dependencies, build config
ci CI/CD GitHub Actions, deployment

4. Identify Scope

Look at changed files to determine scope:

  • Single component: Use component name as scope
  • Multiple related files: Use feature/module name
  • Many unrelated files: Consider splitting commit

5. Generate Commit Message

Format
<type>(<scope>): <subject>

<body>

<footer>
Subject Rules
  • Max 50 characters
  • Imperative mood ("add" not "added")
  • No period at end
  • Lowercase
Body Rules
  • Wrap at 72 characters
  • Explain what and why, not how
  • Separate from subject with blank line
Footer Rules
  • Reference issues: Closes #123
  • Breaking changes: BREAKING CHANGE: description

Read the full file on GitHub · 206 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. 2d ago First seen · 206 lines · 43 tokens per session scan A a744556a6f86

Subscribe to this mod's changes

git-commit is a skill published in the GitHub repository richardcb/oh-my-gemini (16 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 1,131 once invoked, about $0.0002 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 2026-08-30.