commit-message

A guide for writing clear commit messages and pull request descriptions. Conventional Commits is a shared format for describing code changes in a consistent way.

In plain words
What is it for?
Use it to describe staged changes, name commits, summarise branches, and draft pull requests.
Why use it?
It makes the reason for a change understandable later, even to someone who did not work on it, and keeps commits easier to review, undo, or investigate.

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/code-saurabh/openskills/commit-message
Any agent
npx skills add CODE-SAURABH/OpenSkills --skill commit-message
Clone the repo
git clone --depth 1 https://github.com/CODE-SAURABH/OpenSkills

Made for: Claude Code, Codex.

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,563 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 $0.00076 $0.02563
Opus 5 $0.00038 $0.01282
Sonnet 5 $0.00015 $0.00513
Haiku 4.5 $0.00008 $0.00256

Measured yesterday against content hash 573e9abb2ff7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

commit-message/SKILL.md · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit Messages & Pull Request Descriptions

Every commit message and PR description is a permanent record. Future engineers — including yourself in six months — will read them to understand why the codebase is the way it is. A bad commit message is a mystery. A good commit message is documentation that never goes stale.

Write commit messages and PR descriptions as if the reader has zero context about what problem you were solving. Because they do.


Commit Message Principles

  • The commit message is for the reader, not the writer. You know what you changed. The message exists for someone reading git log in a year.
  • Why, not what. The diff shows what changed. The commit message must explain why.
  • One commit, one concern. A commit that fixes a bug and refactors a module is two commits. Atomic commits make revert, bisect, and cherry-pick safe and surgical.
  • Present tense, imperative mood. "Add validation" not "Added validation" or "Adds validation". Read the subject as completing: "This commit will ___."
  • Never commit broken code. Every commit on the main branch must compile, pass tests, and leave the system in a working state.

Conventional Commits Format

Every commit follows the Conventional Commits specification:

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

[optional body]

[optional footer(s)]

Type Reference

Type When to use
feat A new feature visible to users or API consumers
fix A bug fix
docs Documentation only changes (README, comments, API docs)
style Formatting changes that do not affect logic (whitespace, semicolons)
refactor Code restructuring that neither fixes a bug nor adds a feature
perf Performance improvement
test Adding or updating tests
build Changes to build system, dependencies, or CI configuration
ci Changes to CI/CD pipeline configuration
chore Maintenance tasks (dependency updates, config tweaks)
revert Revert a previous commit

Read the full file on GitHub · 322 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. yesterday First seen · 322 lines · 76 tokens per session scan A 573e9abb2ff7

Subscribe to this mod's changes

commit-message is a skill published in the GitHub repository CODE-SAURABH/OpenSkills (2 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 2,563 once invoked, about $0.0004 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.