commit-hygiene

commit-hygiene is a skill for Claude Code, Codex from Gentleman-Programming/gentleman-guardian-angel. It costs 0 tokens per session (602 once invoked), scanned A, original, MIT.

A Git commit-formatting guide that keeps commit messages consistent and the project history readable. It uses formats such as `feat: add login` or `fix(cli): handle errors`.

In plain words
What is it for?
Creating, reviewing, or cleaning up commits and branches in GGA, including changes to providers, hooks, caching, the command-line interface, configuration, installation, and CI.
Why use it?
It removes guesswork about how to name commits and makes changes easier to scan, review, and group.

Skill for Claude CodeCodex

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

Good fit Creating, reviewing, or cleaning up commits and branches in GGA, including changes to providers, hooks, caching, the command-line interface, configuration, installation, and CI.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gentleman-programming/gentleman-guardian-angel/commit-hygiene
About the project

Gentleman Guardian Angel is an AI code-review tool that checks staged files against a repository’s coding standards. Developers use it as a Git pre-commit hook or to review full pull requests, with different AI providers available. The catalogue add-ons support its workflows.

Gentleman-Programming/gentleman-guardian-angel · 1,145 stars · on GitHub

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 Gentleman-Programming/gentleman-guardian-angel --skill commit-hygiene
Clone the repo
git clone --depth 1 https://github.com/Gentleman-Programming/gentleman-guardian-angel

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 commit-hygiene

README.md
[![agentmods](https://agentmods.dev/badge/skills/gentleman-programming/gentleman-guardian-angel/commit-hygiene/github.svg)](https://agentmods.dev/skills/gentleman-programming/gentleman-guardian-angel/commit-hygiene)
Your own site
<a href="https://agentmods.dev/skills/gentleman-programming/gentleman-guardian-angel/commit-hygiene"><img src="https://agentmods.dev/badge/skills/gentleman-programming/gentleman-guardian-angel/commit-hygiene/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 commit-hygiene

Your own site · 80×15
<a href="https://agentmods.dev/skills/gentleman-programming/gentleman-guardian-angel/commit-hygiene"><img src="https://agentmods.dev/badge/skills/gentleman-programming/gentleman-guardian-angel/commit-hygiene.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 602 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 $0.00000 $0.00602
Opus 5 $0.00000 $0.00301
Sonnet 5 $0.00000 $0.00120
Haiku 4.5 $0.00000 $0.00060

Measured 9d ago against content hash 4de554b12ee2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

commit-hygiene 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 9d 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/commit-hygiene/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: gga-commit-hygiene

Purpose

Enforce conventional commits and a clean, readable history for GGA.

When to Use

Any commit creation, review, or branch cleanup.

Format

type(scope): description

Validated by regex:

^(build|chore|ci|docs|feat|fix|perf|refactor|revert|style|test)(\([a-z0-9\._-]+\))?!?: .+

Valid Types

Type Use For
feat New feature or behavior
fix Bug fix
docs Documentation only
chore Maintenance, dependencies, tooling
refactor Restructuring without behavior change
test Adding or fixing tests
ci CI/CD pipeline changes
style Formatting, whitespace, no logic change
perf Performance improvement
build Build system, Makefile changes
revert Reverting a previous commit

Valid Scopes for GGA

Scope Covers
providers lib/providers.sh, any AI provider integration
hooks Hook system, marker injection, pre-commit logic
cache lib/cache.sh, hash logic
cli bin/gga flags, argument parsing, output
ci GitHub Actions workflows
config .gga config file parsing
install install.sh, uninstall.sh

Critical Rules

  • NEVER add Co-Authored-By or any AI attribution trailers
  • One logical change per commit — no "add X and fix Y and update docs"
  • Use imperative mood: "add" not "added", "fix" not "fixed"
  • Reference issue numbers when relevant: feat(providers): add GitHub Models support (#12)
  • Keep subject line ≤ 72 characters
  • If a commit needs explanation, add a body separated by a blank line

Examples

feat(providers): add GitHub Models provider support
fix(hooks): resolve marker injection in existing hooks
fix(cache): handle hash collision on empty files
test(cache): add unit tests for hash invalidation
test(hooks): add integration tests for marker injection
refactor(cli): extract provider dispatch to lib/providers.sh
ci: split unit and integration test jobs
docs(contributing): add label system documentation
chore: update shellspec to 0.28.1

Read the full file on GitHub · 86 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. 9d ago First seen · 86 lines · 0 tokens per session scan A 4de554b12ee2

Subscribe to this mod's changes

commit-hygiene is a skill published in the GitHub repository Gentleman-Programming/gentleman-guardian-angel (1,145 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 602 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.