Git Commit Writer

A tool that writes Git commit messages from staged changes or a code diff. It follows Conventional Commits, a shared format that labels changes such as features, fixes, tests, and documentation.

In plain words
What is it for?
Use it to produce a concise commit subject, an optional explanatory body, and an appropriate change type and scope.
Why use it?
It saves time and keeps commit history consistent and easier to search or use for release automation.

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/notysoty/openagentskills/git-commit-writer
Any agent
npx skills add Notysoty/openagentskills --skill git-commit-writer
Clone the repo
git clone --depth 1 https://github.com/Notysoty/openagentskills

Made for: Claude Code, Codex.

Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,220 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 $0.00016 $0.01220
Opus 5 $0.00008 $0.00610
Sonnet 5 $0.00003 $0.00244
Haiku 4.5 $0.00002 $0.00122

Measured 2d ago against content hash aec0cbb19388, 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 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 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-writer/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Commit Writer

What this skill does

This skill directs the agent to read a git diff (or a plain description of changes) and produce a well-formed commit message following the Conventional Commits specification. It chooses the right type (feat, fix, chore, docs, refactor, test, style, perf, ci), picks an appropriate scope, writes a concise subject line, and — when the change is large enough to warrant it — adds a descriptive body.

Use this when you want consistent, meaningful commit history without having to remember the format every time.

How to use

Claude Code / Cline

Copy this file to .agents/skills/git-commit-writer/SKILL.md in your project root.

Then ask the agent:

  • "Write a commit message for my staged changes using the Git Commit Writer skill."
  • "Here's a diff. Use the Git Commit Writer skill to produce a commit message."

For Claude Code, you can also run git diff --staged first and paste the output into the chat.

Cursor

Add the contents of the "Prompt / Instructions" section below to your .cursorrules file, or paste it into the Cursor AI pane before asking for a commit message.

Codex

Paste the diff into the Codex chat along with the instructions from the section below. Codex works best when you include the full diff rather than a summary.

The Prompt / Instructions for the Agent

When asked to write a commit message, follow these steps:

  1. Read the diff. If not provided, ask for git diff --staged output. Understand every file changed.

  2. Determine the commit type using these rules:

    • feat — a new feature or behavior visible to users or callers
    • fix — a bug fix
    • refactor — code restructuring with no behavior change
    • perf — performance improvement
    • test — adding or fixing tests
    • docs — documentation only (README, comments, etc.)
    • style — formatting, whitespace, lint (no logic change)
    • chore — build scripts, dependencies, tooling
    • ci — CI/CD pipeline changes

Read the full file on GitHub · 128 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 · 128 lines · 16 tokens per session scan A aec0cbb19388

Subscribe to this mod's changes

Git Commit Writer is a skill published in the GitHub repository Notysoty/openagentskills (9 stars, last pushed 18d ago), licensed MIT. It adds 16 tokens to every session and 1,220 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

tui-screen

Create TUI screens, components, and views for the agents-in-a-box terminal UI. Use when building new ratatui components, adding panels, creating list views, or styling any terminal interface element. Provides color palette, component patterns, and quality checklist.

stevengonsalvez/agents-in-a-box · 56 tokens

ship-it

End-to-end ship loop: atomic commits, PR, tiered review (lite|heavy), fix every finding, re-review until zero remain, then merge-commit. lite runs a single /review pass; heavy spins up a dynamic Workflow with diff-aware review personas plus a Codex cross-model peer. Use when Stevie says "/ship-it", "ship it", "ship…

stevengonsalvez/agents-in-a-box · 96 tokens

tmux-ui-tripwire

Write or debug tmux-driven end-to-end TUI tests ("tripwires") for the ainb terminal app. Use when the user asks to "write a tmux test", "add a tripwire", "verify the TUI in tmux", "test feature X by pressing key Y", "validate plugin Z renders", or when editing any file under crates/ainb-core/tests/tripwire.rs.…

stevengonsalvez/agents-in-a-box · 185 tokens

tmux-verify

The outer "is this TUI feature ACTUALLY done?" proof loop for the ainb terminal app. Use when the user asks to "verify the TUI is actually done", "prove this TUI feature works", "validate per tmux-verify", "vhs verify each journey", "frame-truth check the UI", "is the diff actually shown correctly", or to define the…

stevengonsalvez/agents-in-a-box · 231 tokens

ainb-fleet:daemons

Runtime-health view of the four fleet daemons — phone bridge, notifyd, ATC, and the fleet auto-continue daemon — in one table. Each row reports state (running / stopped / unknown), pid, uptime, last activity, error count, and a HEALTH reason that distinguishes a clean stop from a crash (stale heartbeat) or a…

stevengonsalvez/agents-in-a-box · 126 tokens

ainb-fleet:standup

Show fleet status — every claude session running on the host, merged across ainb + claude-peers broker + background jobs. Use when you need to enumerate sessions before composing an action, check the summary of each session, or pipe the list into jq for filtering. (Writes go via tmux by default; a peerid is just an…

stevengonsalvez/agents-in-a-box · 113 tokens