commit-helper

A guide for writing Git commit messages in Conventional Commits format, such as feat for a feature or fix for a bug.

In plain words
What is it for?
Use it to inspect staged changes and recent commits, classify the change, choose an optional scope, and draft a subject, body, and footer.
Why use it?
It turns a set of code changes into a consistent message that explains the change and matches the project's history.

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/curiouslearner/devkit/commit-helper
Any agent
npx skills add CuriousLearner/devkit --skill commit-helper
Clone the repo
git clone --depth 1 https://github.com/CuriousLearner/devkit

Made for: Claude Code, Codex.

Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 577 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 $0.00013 $0.00577
Opus 5 $0.00006 $0.00289
Sonnet 5 $0.00003 $0.00115
Haiku 4.5 $0.00001 $0.00058

Measured yesterday against content hash 28395eeaa38c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

commit-helper 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/commit-helper/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit Helper Skill

Intelligent commit message generation following conventional commit format.

Instructions

You are a git commit message expert. When invoked:

  1. Review Changes: Analyze staged changes using git diff --staged

  2. Categorize Changes: Determine the commit type:

    • feat: New feature
    • fix: Bug fix
    • docs: Documentation only
    • style: Code style (formatting, missing semicolons, etc.)
    • refactor: Code refactoring (no functional changes)
    • perf: Performance improvements
    • test: Adding or updating tests
    • chore: Maintenance tasks (deps, build, etc.)
    • ci: CI/CD changes
    • revert: Revert a previous commit
  3. Identify Scope: Determine the affected component/module (optional but recommended)

  4. Write Message: Generate a commit message following this format:

    <type>(<scope>): <subject>
    
    <body>
    
    <footer>
    
  5. Review History: Check recent commits with git log --oneline -10 to match the project's style

Commit Message Rules

  • Subject line:

    • Max 50 characters
    • Imperative mood ("add" not "added" or "adds")
    • No period at the end
    • Lowercase after type (e.g., "feat: add user authentication")
  • Body (optional):

    • Wrap at 72 characters
    • Explain the "what" and "why", not the "how"
    • Separate from subject with blank line
  • Footer (optional):

    • Reference issues: Fixes #123
    • Breaking changes: BREAKING CHANGE: description

Usage Examples

@commit-helper
@commit-helper --scope api
@commit-helper --type fix

Example Commits

feat(auth): add JWT token refresh mechanism

Implement automatic token refresh to improve user experience
and reduce authentication failures.

- Add refresh token endpoint
- Update auth middleware to handle token expiry
- Add token refresh logic to client

Fixes #456
fix(validation): handle null values in email validator

Previous implementation threw error on null input.
Now returns false for null/undefined values.

Read the full file on GitHub · 98 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 · 98 lines · 13 tokens per session scan A 28395eeaa38c

Subscribe to this mod's changes

commit-helper is a skill published in the GitHub repository CuriousLearner/devkit (27 stars, last pushed 10mo ago), licensed MIT. It adds 13 tokens to every session and 577 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 2026-08-30.

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