git-commit

A guide for writing Conventional Commits, a standard format for describing changes in Git. It reviews the current changes before suggesting a concise commit message in Chinese.

In plain words
What is it for?
Use it when preparing a commit, checking which files changed, separating unrelated work, and creating a commit message such as a feature, fix, test, documentation, or maintenance change.
Why use it?
It avoids vague commit messages and reduces the chance of accidentally committing secrets, build files, logs, or 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/garyfigno/dr.wangagent/git-commit
Any agent
npx skills add GaryFigno/Dr.WangAgent --skill git-commit
Clone the repo
git clone --depth 1 https://github.com/GaryFigno/Dr.WangAgent

Made for: Claude Code, Codex.

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 418 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 $0.00418
Opus 5 $0.00021 $0.00209
Sonnet 5 $0.00008 $0.00084
Haiku 4.5 $0.00004 $0.00042

Measured yesterday against content hash 68d3d2ea9c9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-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 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.

skills/git-commit/SKILL.md · 44 lines

What it actually says

规范 git 提交

步骤

  1. 先看改动范围,绝不盲写:

    git status --short
    git diff --stat
    
  2. 检查是否混入了不该提交的东西(密钥、构建产物、日志)。发现 config.yaml.envcredentials.jsondist/build/ 等,先让用户确认,不要自行加入。

  3. 按改动写提交信息,格式:

    <type>(<scope>): <中文简述>
    
    • feat 新功能
    • fix 修 bug
    • refactor 重构(不改行为)
    • docs 文档
    • test 测试
    • chore 杂务(依赖、构建、格式化)

    scope 是可选的影响模块,如 feat(quest): 步骤失败自动重试

  4. 一次提交只做一件事:改动跨多个无关主题时,用 git add <path> 分开提交。

  5. 提交前展示命令让用户确认(除非已获授权直接执行):

    git commit -m "<message>"
    

红线

  • 提交前必须 git status 确认暂存区范围
  • 不提交 .gitnode_modules.venvdist/build/、密钥与日志文件
  • 不替用户改写他人未提交的改动
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. yesterday First seen · 44 lines · 42 tokens per session scan A 68d3d2ea9c9b

Subscribe to this mod's changes

git-commit is a skill published in the GitHub repository GaryFigno/Dr.WangAgent (2 stars, last pushed 13d ago), licensed MIT. It adds 42 tokens to every session and 418 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.