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.
npx agentmods add skills/codebygarv/ai-skills/commit-message-expertnpx skills add codebygarv/Ai-skills --skill commit-message-expertgit clone --depth 1 https://github.com/codebygarv/Ai-skillsWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00043 | $0.00517 |
| Opus 5 | $0.00022 | $0.00259 |
| Sonnet 5 | $0.00009 | $0.00103 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
commit-message-expert 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Write a clear, well-structured commit message for a given change — one that explains what changed and, where non-obvious, why, following the project's commit convention (Conventional Commits by default unless another pattern is evident).
When to Use
- Writing a commit message for a diff/change and want it done well.
- Reviewing an existing commit message for clarity/convention compliance.
- A project's commit history is inconsistent and needs a documented convention to follow going forward.
What to Analyze / Do
- Determine the convention in use — check recent commit history for a pattern (Conventional Commits
type(scope): subject, or a different house style) and match it; default to Conventional Commits if none is evident. - Identify the actual change type —
feat,fix,refactor,docs,test,chore,perf, etc. — based on what the diff actually does, not what the author might casually call it. - Write a subject line — imperative mood ("add" not "added"/"adds"), no trailing period, under ~72 characters, specific enough to be useful in a
git log --onelinescan. - Write a body when the "why" isn't obvious from the diff alone — motivation, context, trade-offs considered. Skip the body entirely for genuinely self-explanatory changes; an empty body isn't a defect.
- Flag breaking changes — using the convention's mechanism for it (e.g.
BREAKING CHANGE:footer in Conventional Commits, or!after the type/scope).
Output Format
- Subject line first.
- Blank line, then body (only if it adds real information beyond the subject).
- Footer for breaking changes/issue references if applicable.
- If reviewing an existing message rather than writing a new one: state what's good, what's unclear, and a rewritten version.
Avoid
- Vague subjects like "fix stuff," "update code," "misc changes" — every commit message should say what actually changed.
- Writing a body that just restates the subject in different words without adding context.
- Forcing Conventional Commits format onto a project that clearly uses a different, established convention.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 36 lines · 43 tokens per session scan A 5ec011b40124
commit-message-expert is a skill published in the GitHub repository codebygarv/Ai-skills (24 stars, last pushed 13d ago), licensed MIT. It adds 43 tokens to every session and 517 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.
Other skills, from other repositories
git-commit
Conventional Commits format for git commits and PR/MR titles. Type prefixes, scope rules, breaking change syntax, and commit message structure. Use when committing changes, writing commit messages, creating PR/MR titles, or formatting squash merge messages. Not for PR workflows (git-pr), CI/CD status (git-ci), or git…
ship
Build, commit, push & version bump workflow - automates the complete release cycle.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
chinese-commit-conventions
中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用，不要根据上下文自动触发。.
commit-push-pr
Commit selected local changes, push the branch, and create or update a GitHub pull request with BitFun attribution. Use when the user asks to 提交 PR、提代码、commit and push、开 PR、create a pull request, or wants a Claude Code-like one-command PR publishing flow from BitFun.
commit-push-pr
Commit current changes, push to remote, and create or update a pull request. Use when the user wants to commit and create a PR, push changes and open a pull request, or ship their current work as a PR.