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/luqiang-code/claude-code-skills/git-commit-generatornpx skills add luqiang-code/claude-code-skills --skill git-commit-generatorgit clone --depth 1 https://github.com/luqiang-code/claude-code-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 | $0.00055 | $0.00533 |
| Opus 5 | $0.00028 | $0.00267 |
| Sonnet 5 | $0.00011 | $0.00107 |
| Haiku 4.5 | $0.00006 | $0.00053 |
Grade A, and why
git-commit-generator 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.
What it actually says
Git Commit Generator
Generate Conventional Commits from staged changes.
When to Use
- Ready to commit and want a properly formatted message
- Team enforces Conventional Commits standard
- User mentions "commit", "conventional commit", "commit message"
When NOT to Use
- No staged changes yet
- Interactive rebase or amend workflows (different context)
Workflow
- Run
git diff --cachedto get staged changes - Run
git diff --cached --statfor file overview - Analyze: determine type (feat/fix/refactor/docs/test/chore) and scope
- Generate commit message:
- Type(scope): short description (under 72 chars)
- Blank line
- Body: WHAT changed and WHY (wrapped at 72 chars)
- Footer: breaking changes or issue references if applicable
- Show the message and ask user to confirm before committing
Output Format
feat(auth): add JWT refresh token rotation
Introduce automatic refresh token rotation to prevent token replay
attacks. Old refresh tokens are invalidated when a new one is issued.
BREAKING CHANGE: /api/auth/refresh now returns { accessToken, refreshToken }
Closes #234
Key Principles
- Type must be one of: feat, fix, refactor, docs, test, chore, perf, ci, style
- Subject line: imperative mood ("add" not "added"), no period at end
- Body explains WHY, not just WHAT
- Reference issues with "Closes #N" or "Refs #N"
- Breaking changes MUST be flagged in footer
Notes
- If diff is large (>500 lines), suggest splitting into multiple commits
- If no Conventional Commits type clearly fits, default to "chore"
- Never commit automatically — always ask for confirmation
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.
- yesterday First seen · 67 lines · 55 tokens per session scan A 62c15f5a0fd5
git-commit-generator is a skill published in the GitHub repository luqiang-code/claude-code-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 533 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.
Other skills, from other repositories
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
golden-chat
Use when testing the goldenchat golden build.
golden-epub
Use when testing the epub golden build.
golden-epub-kw
Use when testing keyword categorization.
golden-html-multi
Use when testing the multi-file html build.
golden-jupyter-dir
Use when testing the goldenjupyterdir golden build.