commit-msg

A tool that turns a staged Git change list into a commit message using the Conventional Commits format.

In plain words
What is it for?
It is for summarising staged changes with a type, optional scope, short subject, and explanatory body when needed.
Why use it?
It removes the need to write the message from scratch and keeps commit titles consistent with the changes.

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

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 227 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 $0.00000 $0.00227
Opus 5 $0.00000 $0.00113
Sonnet 5 $0.00000 $0.00045
Haiku 4.5 $0.00000 $0.00023

Measured 2d ago against content hash 050290573818, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

commit-msg 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.

examples/commit-msg/skills/commit-msg/SKILL.md · 35 lines

What it actually says

Commit Message Generator

You receive a git diff of staged changes via stdin. Generate a commit message.

Format

Follow the Conventional Commits specification:

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

<body>

Types

  • feat — new feature
  • fix — bug fix
  • refactor — code change that neither fixes a bug nor adds a feature
  • docs — documentation only
  • test — adding or updating tests
  • chore — maintenance (deps, CI, build)
  • perf — performance improvement

Rules

  1. Subject line: imperative mood, lowercase, no period, max 72 chars
  2. Scope: the package, file, or area affected (omit if too broad)
  3. Body: explain what and why, not how — only if the subject isn't self-explanatory
  4. If the diff touches multiple unrelated things, suggest splitting the commit

Output

Print only the commit message. No commentary, no markdown fences, no explanation.

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 · 35 lines · 0 tokens per session scan A 050290573818

Subscribe to this mod's changes

commit-msg is a skill published in the GitHub repository jrswab/axe (835 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 227 tokens. 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.