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/bosens-china/tc39-atlas/git-step-commitnpx skills add bosens-China/tc39-atlas --skill git-step-commitgit clone --depth 1 https://github.com/bosens-China/tc39-atlasWrote 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.
[](https://agentmods.dev/skills/bosens-china/tc39-atlas/git-step-commit)<a href="https://agentmods.dev/skills/bosens-china/tc39-atlas/git-step-commit"><img src="https://agentmods.dev/badge/skills/bosens-china/tc39-atlas/git-step-commit.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00134 | $0.05040 |
| Opus 5 | $0.00067 | $0.02520 |
| Sonnet 5 | $0.00027 | $0.01008 |
| Haiku 4.5 | $0.00013 | $0.00504 |
Grade A, and why
git-step-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 5d 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 — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Step Commit
把当前 Git 更改整理成清晰、可审查、可回滚的提交。
管理持久偏好
当用户要求设置、查看或删除提交偏好时,只处理配置并返回结果,不检查工作树、不规划提交,也不提交文件。使用 Git 原生配置,不依赖 Skill 携带的脚本或额外运行时。
使用两个配置项:
git-step-commit.mode:只允许default、review或direct。git-step-commit.language:允许auto或规范化的语言标识。把常见自然语言名称转换为稳定标识,例如中文为zh-CN、英文为en、日文为ja、韩文为ko;其他值使用合法的 BCP 47 形式,不确定时先询问,不写入猜测值。
使用两个作用域:
- 全局:使用
git config --global,对该用户的所有项目生效。 - 当前项目:使用
git config --local,只写入当前仓库的 Git 配置,不写入或提交项目文件。执行前确认位于 Git 仓库中。
写入或删除时必须知道作用域。用户未说明且无法从上下文确定时先询问,不要擅自选择全局或当前项目。读取未指定作用域时默认显示当前有效值及来源。
读取
使用当前终端直接执行以下 Git 命令;不要要求 Bash、Python 或 Go。分别读取各层,按字段解析:
git config --local --get git-step-commit.mode
git config --local --get git-step-commit.language
git config --global --get git-step-commit.mode
git config --global --get git-step-commit.language
不在 Git 仓库中时跳过 --local。读取不存在的 key 所产生的非零退出码表示“未设置”,不是工作流失败。显示每个字段的有效值和来源:本次指令、当前项目、全局或内置。
写入
先校验并规范化所有值,再使用对应作用域执行一个或两个精确命令:
git config --global --replace-all git-step-commit.mode review
git config --global --replace-all git-step-commit.language zh-CN
git config --local --replace-all git-step-commit.mode direct
git config --local --replace-all git-step-commit.language auto
只修改用户明确给出的字段。写入后从同一作用域读回并核对;命令失败或读回不一致时说明真实结果,不要声称配置成功。
删除
删除单个字段时执行对应的 --unset-all:
git config --global --unset-all git-step-commit.mode
git config --local --unset-all git-step-commit.language
删除指定作用域的全部提交偏好时执行:
git config --global --remove-section git-step-commit
git config --local --remove-section git-step-commit
只删除用户指定的字段和作用域。目标不存在所产生的非零退出码表示原本已无配置,按幂等成功处理。删除后读取有效值并说明回退到了哪一层。
选择模式
- 每次实际提交请求开始时静默读取项目和全局的两个配置项,即使用户本轮没有提到偏好;把读取放进下方的一次性分析调用,避免增加往返。
- 对
mode按“本次明确指令 → 当前项目配置 → 全局配置 → 内置默认”逐层取值。只要当前项目存在该 key,就停止向全局回退;因此项目级default可以明确恢复内置行为。 default:使用内置行为。对“帮我提交”“git commit”“分步提交”等普通请求先输出计划并等待确认;本次明确说“按推荐提交”“你决定并直接提交”“无需确认”等授权时直接提交。review:默认输出计划并等待确认。direct:默认内部完成分析并直接提交全部推荐批次。- 本次明确说“本次直接提交”或“本次先审查”时,临时覆盖持久模式但不修改配置。
- 如果用户只询问“推荐怎么提交”“给我建议”或只要求审查,无论持久模式为何都只输出计划。
What ships with it
1 file 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.
- 5d ago First seen · 301 lines · 134 tokens per session scan A f2006ecf4809
git-step-commit is a skill published in the GitHub repository bosens-China/tc39-atlas (0 stars, last pushed yesterday), licensed MIT. It adds 134 tokens to every session and 5,040 once invoked, about $0.0007 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
review-pr
Review a Deno runtime pull request for correctness, tests, security, and conventions. Use when asked to review a PR or when a PR number/URL is provided for review.
adev-writing-guide
Comprehensive writing guide for Angular documentation (adev). Covers Google Technical Writing standards, Angular-specific markdown extensions, code blocks, and components. You MUST use this skill any time you plan to create, edit, or review documentation files in adev/ or adev/src/content.
reference-signal-forms
Explains the mental model and architecture of the code under packages/forms/signals. You MUST use this skill any time you plan to work with code in packages/forms/signals.
fmt
Format all code in the repository. Run before opening a PR or committing changes.
lint-js
Lint JS/TS code only. Use before opening a PR when only JavaScript or TypeScript files were changed (no Rust).
angular-developer
Generates Angular code and provides architectural guidance. Trigger when creating projects, components, services, or HTTP communication, or for best practices on reactivity (signals, linkedSignal, resource, httpResource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component…