commit-hygiene

A set of rules for writing useful Git commit messages and grouping changes into clear, reviewable commits.

In plain words
What is it for?
Use it when planning commit boundaries, writing commit messages, or deciding whether a changeset should be split.
Why use it?
It prevents vague history and mixed-purpose commits from making it difficult to understand, review, or undo 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/nrdxp/predicate/commit-hygiene
Any agent
npx skills add nrdxp/predicate --skill commit-hygiene
Clone the repo
git clone --depth 1 https://github.com/nrdxp/predicate

Made for: Claude Code, Codex.

Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,401 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 $0.00098 $0.02401
Opus 5 $0.00049 $0.01201
Sonnet 5 $0.00020 $0.00480
Haiku 4.5 $0.00010 $0.00240

Measured yesterday against content hash bce22b60c3af, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/check_commit_msg.py, scripts/test_check_commit_msg.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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 · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit Hygiene

Guidelines and constraints for writing clear, structured, and reviewer-centric git commit messages. Every commit is a unit of structured information designed to optimize human comprehension and git history utility.

Purpose

The goal of commit hygiene is not formatting for its own sake. The goal is a clean, human-reviewable git history.

A well-maintained history lets a human reviewer reconstruct the reasoning behind a codebase by reading git log. Every commit should answer: what changed, why it changed, and where the logical boundary of that change is. When history achieves this, it becomes a durable decision record — not just a log of file mutations.

This requires two things working together:

  1. Good commit messages — clear, structured, motivated (covered by the formatting and communication rules below).
  2. Commits at logical boundaries — each commit captures one coherent unit of change with a reviewable diff (covered by the Atomicity and Boundary Discipline section below).

Neither is sufficient alone. A perfectly formatted message attached to a 40-file spaghetti diff is useless. A clean single-file diff with a message that says "update stuff" is nearly as bad. Both disciplines are required, always — not only when a formal workflow like C.O.R.E. is active.

Hard Constraints

All commit messages MUST satisfy these structural invariants:

  1. Header Line Limit: The summary line MUST NOT exceed 50 characters.
  2. Body Line Limit: No line in the body or footer may exceed 72 characters.
  3. Blank Line Separation: A single blank line MUST separate the header from the body.

Conventional Commits Structure

Commits must conform to the Conventional Commits v1.0.0 specification:

<type>(<scope>)[!]: <description>

[optional body]

[optional footer(s)]

Breaking Changes

A breaking change must be indicated by:

  • An exclamation mark ! suffixing the type or scope in the summary header (e.g., feat!: remove deprecated api or fix(parser)!: adjust breaking parser logic).
  • A BREAKING CHANGE: <description> footer entry.

Read the full file on GitHub · 202 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 202 lines · 98 tokens per session scan A bce22b60c3af

Subscribe to this mod's changes

commit-hygiene is a skill published in the GitHub repository nrdxp/predicate (10 stars, last pushed 8d ago), licensed MIT. It adds 98 tokens to every session and 2,401 once invoked, about $0.0005 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens