conventional-commit

conventional-commit is a skill for Claude Code, Codex from MuhammadUsmanGM/claude-code-best-practices. It costs 42 tokens per session (462 once invoked), scanned A, original, MIT.

A workflow for writing a Conventional Commits message, a standard format that labels a change such as a feature, fix, test, or documentation update. It can also create the commit when asked.

In plain words
What is it for?
It helps inspect staged or unstaged diffs, choose a commit type and scope, write a concise subject and optional body, and commit approved work.
Why use it?
It avoids vague or inconsistent commit messages and bases the message on the actual staged changes and the repository's existing style.

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/muhammadusmangm/claude-code-best-practices/conventional-commit
Any agent
npx skills add MuhammadUsmanGM/claude-code-best-practices --skill conventional-commit
Clone the repo
git clone --depth 1 https://github.com/MuhammadUsmanGM/claude-code-best-practices

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 conventional-commit

README.md
[![agentmods](https://agentmods.dev/badge/skills/muhammadusmangm/claude-code-best-practices/conventional-commit.svg)](https://agentmods.dev/skills/muhammadusmangm/claude-code-best-practices/conventional-commit)
Your own site
<a href="https://agentmods.dev/skills/muhammadusmangm/claude-code-best-practices/conventional-commit"><img src="https://agentmods.dev/badge/skills/muhammadusmangm/claude-code-best-practices/conventional-commit.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 462 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 $0.00042 $0.00462
Opus 5 $0.00021 $0.00231
Sonnet 5 $0.00008 $0.00092
Haiku 4.5 $0.00004 $0.00046

Measured 3d ago against content hash dfc3fb37f8c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

conventional-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 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.

plugins/commit-helper/skills/conventional-commit/SKILL.md · 35 lines

What it actually says

Conventional Commit

You are being invoked to turn the current staged diff into a single, well-formed Conventional Commits message.

Steps

  1. Run git status --short and git diff --cached --stat. If nothing is staged, run git diff --stat and ask the user whether to stage everything or a subset. Do not guess.
  2. Run git diff --cached (or git diff if nothing staged yet) to read the actual changes.
  3. Run git log -10 --oneline to match the repo's existing commit style (scope naming, casing).
  4. Draft a message:
    • type: one of feat|fix|docs|refactor|perf|test|chore|build|ci|style|revert
    • scope: optional, derived from the top-level directory or package touched
    • subject: imperative, ≤ 72 chars, no trailing period
    • body: only if the why isn't obvious from the subject. Wrap at 72.
    • footer: BREAKING CHANGE: or Closes #123 only when applicable
  5. Show the message to the user and ask for confirmation unless they already said "commit it" / "just commit."
  6. On confirmation, run git commit -m "..." using a heredoc for multi-line bodies.

Rules

  • Never include Co-Authored-By lines unless the user asks.
  • Never git push.
  • Never --amend a commit that's already been pushed.
  • If pre-commit hooks fail, fix the underlying issue and create a new commit. Do not --no-verify.

Output

After committing, print the short SHA and subject line. Nothing else.

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 · 35 lines · 42 tokens per session scan A dfc3fb37f8c4

Subscribe to this mod's changes

conventional-commit is a skill published in the GitHub repository MuhammadUsmanGM/claude-code-best-practices (76 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 462 once invoked, about $0.0002 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.