commit

A workflow for creating short conventional commit messages, which follow a shared format such as a change type and brief subject. It can inspect changes, run available pre-commit checks, stage files, and create commits.

In plain words
What is it for?
Use it when staging and committing work, writing a commit message, running pre-commit checks, or deciding whether a change should be split into atomic commits.
Why use it?
It gives commits a consistent format and catches available checks before saving changes. It can also flag when one diff contains separate concerns that should become separate commits.

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

Made for: Claude Code, Codex.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 766 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 $0.00055 $0.00766
Opus 5 $0.00028 $0.00383
Sonnet 5 $0.00011 $0.00153
Haiku 4.5 $0.00006 $0.00077

Measured yesterday against content hash 47e3b3239ab0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

plugins/git-workflow/skills/commit/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit - Conventional Commit Messages

Creates commits with short conventional commit messages. Runs pre-commit checks and suggests splitting when the staged changes cover more than one concern.

Usage

/git-workflow:commit [--no-verify] [--help]

Workflow

  1. Pre-commit checks (unless --no-verify): run make checks if available.
  2. Git analysis: inspect staged files and git diff to identify the change.
  3. Commit: write the message, then commit.

If nothing is staged, stage all modified files. If the diff covers distinct concerns, propose atomic commits before committing.

Message Rules

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

[body — only when required]
  • No emoji. Not in the subject, not in the body.
  • Subject: imperative mood, lower case, no trailing period, under 60 characters.
  • scope is optional; include it only when it disambiguates.
  • Default to a subject line alone. Most commits need nothing more.
  • Add a body only for information the diff cannot show: why the change was made, a breaking change, or an issue reference. Cap it at two short sentences or three bullets.
  • Never restate the diff, list touched files, summarise your process, or add closing commentary.

Types

  • feat: new feature
  • fix: bug fix, security fix, warning fix
  • docs: documentation
  • style: formatting
  • refactor: restructuring without behaviour change
  • perf: performance
  • test: tests
  • chore: tooling, dependencies, configuration
  • ci: CI/CD

Splitting Criteria

Propose separate commits when the staged changes mix concerns, mix types (feature + fix + docs), or are large enough that one message cannot describe them accurately.

Examples

Good:

  • feat(auth): add session refresh endpoint
  • fix(render): release texture handles on unmount
  • docs: document the scanner exit codes
  • refactor: collapse duplicate error wrapping

With a body, where the reason is not visible in the diff:

fix(scanner): match patterns case-insensitively

Uppercase AWS keys were slipping through, reported in #212.

Read the full file on GitHub · 103 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 · 103 lines · 55 tokens per session scan A 47e3b3239ab0

Subscribe to this mod's changes

commit is a skill published in the GitHub repository rikdc/ai-skills (2 stars, last pushed 19d ago), licensed MPL-2.0. It adds 55 tokens to every session and 766 once invoked, about $0.0003 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