make-git-commit

A guide for creating Git commits using Conventional Commits, a standard format for describing code changes.

In plain words
What is it for?
Use it to choose a commit type, write the subject and body, stage named files, and create a commit from already staged changes.
Why use it?
It keeps commit messages consistent and records breaking changes, issue links, and motivations in the expected format.

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/zerocracy/zealot/make-git-commit
Any agent
npx skills add zerocracy/zealot --skill make-git-commit
Clone the repo
git clone --depth 1 https://github.com/zerocracy/zealot

Made for: Claude Code, Codex.

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 486 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 $0.00027 $0.00486
Opus 5 $0.00014 $0.00243
Sonnet 5 $0.00005 $0.00097
Haiku 4.5 $0.00003 $0.00049

Measured yesterday against content hash fd931f9319e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

make-git-commit 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.

skills/make-git-commit/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Staging

Trust staged state. Commit straight from staged state, leaving edit, lint, test, and build aside. Stage files explicitly with paths user named.

Type

Respect Conventional Commits standard. Pick type from standard set. Hold to that standard set.

Description

Write description in imperative mood, lowercase. Use no trailing period. Keep description under 72 characters. Prepend ticket number with # to description. Do this when commit ties to known issue or pull request.

Breaking

Append ! after type or scope when commit introduces incompatible change. Add BREAKING CHANGE: footer when commit introduces incompatible change.

Body

Keep body to few short sentences. Explain motivation and visible effect. Omit body when subject says enough. Keep message free of restated diffs, file lists, and obvious summaries. Keep each commit to one related change.

Footers

Add Closes #<number> or Fixes #<number> footer only when needed. Add it only when host needs that token to auto-close ticket on merge.

Trailers

Keep every Co-authored-by: trailer free of Claude, Anthropic, and any agent. Leave author and committer identity as Git sets them. Keep message free of advertising trailers, signatures, and emoji. Keep message free of Generated with lines.

Safety

Run hooks and signing as configured unless user asked to bypass them. Confine work to one fresh local commit. Leave amend, rebase, force-push, and push aside.

Verify

Verify commit subject, body, footers, and file set after committing. Create new commit on top rather than amending when something is wrong.

Example

Input: staged src/parser.rs; ties to issue #214; user says "commit it"
git commit produces:
  fix: #214 reject trailing comma in arrays

  The array parser accepted a trailing comma, diverging from the
  JSON grammar. Tighten the lookahead so a stray comma now fails.

  Closes #214

Verified description leads with #214, stays under 72 chars,
lowercase, no trailing period; footer auto-closes the issue.

Read the full file on GitHub · 79 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 · 79 lines · 27 tokens per session scan A fd931f9319e7

Subscribe to this mod's changes

make-git-commit is a skill published in the GitHub repository zerocracy/zealot (4 stars, last pushed 4d ago), licensed MIT. It adds 27 tokens to every session and 486 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

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