commit-message

commit-message is a skill for Claude Code, Codex from sunnykgupta/AI-Helpers. It costs 61 tokens per session (501 once invoked), scanned A, original, MIT.

A guide for writing Git commit messages in the Conventional Commits format, a shared style such as `fix(auth): handle expired tokens`. It chooses a message type and optional scope from the change.

In plain words
What is it for?
Use it when you have a diff or staged changes and need a commit message. It can also suggest splitting a commit when it contains multiple unrelated changes.
Why use it?
It provides a consistent way to describe changes in project history. This avoids vague commit messages and helps separate unrelated 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/sunnykgupta/ai-helpers/commit-message
Any agent
npx skills add sunnykgupta/AI-Helpers --skill commit-message
Clone the repo
git clone --depth 1 https://github.com/sunnykgupta/AI-Helpers

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-message

README.md
[![agentmods](https://agentmods.dev/badge/skills/sunnykgupta/ai-helpers/commit-message.svg)](https://agentmods.dev/skills/sunnykgupta/ai-helpers/commit-message)
Your own site
<a href="https://agentmods.dev/skills/sunnykgupta/ai-helpers/commit-message"><img src="https://agentmods.dev/badge/skills/sunnykgupta/ai-helpers/commit-message.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 501 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 $0.00061 $0.00501
Opus 5 $0.00030 $0.00251
Sonnet 5 $0.00012 $0.00100
Haiku 4.5 $0.00006 $0.00050

Measured 3d ago against content hash 6a984e622d5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

commit-message 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 3d 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.

.opencode/skills/commit-message/SKILL.md · 61 lines

What it actually says

Commit Message Writer

Write commit messages that follow Conventional Commits.

Format

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

<body>

<footer>
  • type (required): one of feat, fix, refactor, test, chore, docs
  • scope (optional): the module/area touched, e.g. auth, api, parser
  • subject (required): imperative mood, lowercase, no period, <= 50 chars
  • body (optional): wrap at 72 chars, explain why not what
  • footer (optional): BREAKING CHANGE: ... or Closes #123

Rules

  • Subject line in imperative mood: "add login form", not "added" or "adds".
  • Blank line between subject and body, and between body and footer.
  • Use ! after type/scope for breaking changes: feat(api)!: drop v1 endpoints.
  • One commit = one logical change. If the diff covers multiple concerns, suggest splitting.
  • Never put file names in the subject. Use scope instead.

Workflow

  1. Ask for the diff or git status output if not provided.
  2. Determine type from the nature of the change (new feature -> feat, bugfix -> fix, etc.).
  3. Pick a scope from the most-touched directory or module.
  4. Write subject, then body only if context is non-obvious.
  5. Add BREAKING CHANGE: footer if applicable.

Examples

feat(auth): add OAuth login via GitHub

Users can now sign in with their GitHub account. Uses the standard
OAuth2 flow; tokens are stored in httpOnly cookies.

Closes #142
fix(parser): handle empty input without crashing
refactor(api)!: rename /users endpoint to /accounts

BREAKING CHANGE: /users is removed. Update clients to use /accounts.
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. 3d ago First seen · 61 lines · 61 tokens per session scan A 6a984e622d5f

Subscribe to this mod's changes

commit-message is a skill published in the GitHub repository sunnykgupta/AI-Helpers (70 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 501 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 2026-08-30.

Related

Other skills, from other repositories