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/leekjay/claude-skills-plugin/git-commit-conventionsnpx skills add LeekJay/claude-skills-plugin --skill git-commit-conventionsgit clone --depth 1 https://github.com/LeekJay/claude-skills-pluginWhat 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 | $0.00046 | $0.01407 |
| Opus 5 | $0.00023 | $0.00704 |
| Sonnet 5 | $0.00009 | $0.00281 |
| Haiku 4.5 | $0.00005 | $0.00141 |
Grade A, and why
git-commit-conventions 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Commit Conventions
Standardize Git commit messages to ensure clear, traceable code history and support automated tooling.
Commit Message Format
Use Conventional Commits style with Chinese subjects:
<type>(<scope>): <Chinese subject>
[optional body]
[optional footer]
Type
feat: New featurefix: Bug fixrefactor: Code refactoring (no functionality change)docs: Documentation updatestest: Test-related changeschore: Build, dependency, or maintenance workstyle: Code formatting (no logic change)perf: Performance optimization
Scope (optional)
Specify the affected module or component:
feat(app):- Application layer changesfix(api):- API layer fixesrefactor(auth):- Authentication module refactoring
Subject
- Must use Chinese
- Use imperative mood (e.g., "添加" not "已添加")
- No capitalization needed for first letter
- No period at the end
- Keep it concise, typically under 50 characters
Strict Rules
❌ ABSOLUTELY PROHIBITED: AI Identifiers
Git commit messages MUST NOT include ANY AI identifiers.
This is a strict, non-negotiable requirement. All of the following are FORBIDDEN:
- ❌ "Generated with Claude Code"
- ❌ "Generated with Claude Code"
- ❌ "Co-Authored-By: Claude [email protected]"
- ❌ "Co-Authored-By: AI"
- ❌ Any AI-related emojis (🤖, 🚀 when combined with AI references)
- ❌ Any mention of AI assistance in commit message body or footer
- ❌ Any URL to Claude Code or AI tool websites
- ❌ Any "Powered by", "Made with", "Assisted by", "Co-Authored-By" followed by AI tool names
Why this matters:
- Commit messages should describe the what and why of changes, not the how they were created
- AI is an assistive tool; the developer is ultimately responsible for all commits
- Professional commit history should focus on code changes, not generation methods
- This maintains consistency and clarity in project history
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 · 182 lines · 46 tokens per session scan A 8edf9156603e
git-commit-conventions is a skill published in the GitHub repository LeekJay/claude-skills-plugin (4 stars, last pushed 8mo ago), licensed MIT. It adds 46 tokens to every session and 1,407 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.