git-commit-writer

git-commit-writer is a skill for Claude Code, Codex from mergisi/awesome-openclaw-agents. It costs 53 tokens per session (647 once invoked), scanned A, original, MIT.

A commit-message drafting helper that reads the changes already staged in Git and suggests a message matching the repository’s style.

In plain words
What is it for?
Use it to review staged changes, write a commit message, or choose a name for a commit. It drafts the message but does not run the commit unless asked.
Why use it?
It removes the guesswork from naming a commit and helps the message explain why the change was made. It also checks that there are staged changes to describe.

Skill for Claude CodeCodex

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

Good fit Use it to review staged changes, write a commit message, or choose a name for a commit. It drafts the message but does not run the commit unless asked.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mergisi/awesome-openclaw-agents/git-commit-writer
About the project

awesome-openclaw-agents is a curated collection of ready-to-use SOUL.md configurations that define AI agents for tasks across areas such as development, marketing, finance, support, and automation. It is for OpenClaw users who want predefined agent roles and workflows to adapt or deploy. The catalogue entries are agent-related skills drawn from this collection.

mergisi/awesome-openclaw-agents · 4,017 stars · on GitHub · crewclaw.com

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 mergisi/awesome-openclaw-agents --skill git-commit-writer
Clone the repo
git clone --depth 1 https://github.com/mergisi/awesome-openclaw-agents

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-writer

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/mergisi/awesome-openclaw-agents/git-commit-writer"><img src="https://agentmods.dev/badge/skills/mergisi/awesome-openclaw-agents/git-commit-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 647 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00053 $0.00647
Opus 5.5 $0.00021 $0.00259
Sonnet 5.5 $0.00011 $0.00129
Haiku 4.5 $0.00005 $0.00065

Measured 1mo ago against content hash a7d6021dd614, 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-writer 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 1mo 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/claude/git-commit-writer/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Commit Writer

Generate a disciplined commit message from the currently staged changes. Opinionated about style: imperative mood, concise title, body that explains why not what.

When to use

  • User says "write a commit message", "/commit", "commit this"
  • User has staged changes and asks to review them before committing
  • User asks "what should this commit be called"

Do NOT use this skill to actually run git commit unless the user explicitly asks — just draft the message and show it.

Instructions

  1. Run git status --short with the Bash tool. Confirm there are staged changes. If nothing is staged, stop and tell the user.
  2. Run git diff --staged to read the full staged diff. If the diff is large (>500 lines), also run git diff --staged --stat to get a file-level overview first.
  3. Run git log --oneline -10 to learn the repo's commit convention. Look for:
    • Conventional Commits prefixes (feat:, fix:, chore:) — if present, match the style.
    • Title case vs sentence case.
    • Whether bodies are used or not.
    • Any ticket / issue prefix (e.g. [PROJ-123]).
  4. Draft a message following these rules:
    • Title: imperative mood ("Add X", not "Added X" or "Adds X"), max 70 characters, no trailing period.
    • Body (if needed): blank line after title, then 1-3 short paragraphs or bullets explaining why the change is necessary, what problem it solves, what trade-offs were made.
    • Never use the word "refactor" alone — always say what was refactored and why ("Extract retry loop into helper to share with job runner").
    • Never write "Update file.js" — describe the behavior change, not the file touched.
    • Never invent a ticket number. If the repo uses them but you can't infer one, leave it out.
  5. Show the drafted message in a fenced code block. Ask the user if they want you to run git commit with it. Do not commit automatically.

Anti-patterns to reject

  • "Various fixes" / "Updates" / "WIP" — reject and ask for specifics from the diff.
  • "Refactor code" — must name the unit being refactored.
  • Title >70 chars — shorten or move detail to body.
  • Past tense or "-ing" forms — rewrite to imperative.

Read the full file on GitHub · 48 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. 1mo ago First seen · 48 lines · 53 tokens per session scan A a7d6021dd614

Subscribe to this mod's changes

git-commit-writer is a skill published in the GitHub repository mergisi/awesome-openclaw-agents (4,017 stars, last pushed 25d ago), licensed MIT. It adds 53 tokens to every session and 647 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

git-workflow

Guides safe, professional Git usage — branching strategies, atomic clean commits, conventional commit messages, interactive rebase (squash/fixup/reword/reorder), merge vs rebase decisions, conflict resolution, and recovery of lost work via reflog. Use this skill when the user asks to create or clean up a branch, write…

JayRHa/AgentSkills · 132 tokens

caveman-commit

Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.

JuliusBrussee/caveman · 38 tokens

git

Source-control safety for Git. Two rules apply whether or not you read the body. First, never commit, amend, push, tag, rebase, cherry-pick, revert, or reset --hard unless the user asked for that exact write in this session. An explicit request to create a new commit counts anywhere in the user's own task text, but it…

asgeirtj/system_prompts_leaks · 163 tokens

git-advanced-workflows

Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.

wshobson/agents · 54 tokens

changelog

Auto-generate a changelog from git commits and sprint data. Internal and player-facing versions.

Donchitos/Claude-Code-Game-Studios · 22 tokens

workflow-patterns

Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.

wshobson/agents · 35 tokens