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/iceymoss/go-hichat-api/git-commitnpx skills add iceymoss/go-hichat-api --skill git-commitgit clone --depth 1 https://github.com/iceymoss/go-hichat-apiWhat 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 | $0.00041 | $0.01402 |
| Opus 5 | $0.00020 | $0.00701 |
| Sonnet 5 | $0.00008 | $0.00280 |
| Haiku 4.5 | $0.00004 | $0.00140 |
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 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Commit
根据仓库历史使用简化的 Conventional Commits 规范生成提交信息;只有用户明确要求提交代码时才执行 git commit。
提交格式
<type>[(scope)]: <description>
[body]
[footer]
Type
优先使用仓库历史中已有的类型:
| Type | 用途 |
|---|---|
feat |
新增或扩展用户可感知的功能 |
fix |
修复缺陷或错误行为 |
docs |
仅修改文档 |
chore |
工具、依赖、仓库配置等维护工作 |
ci |
CI/CD、镜像构建或部署流水线变更 |
perf |
性能优化 |
refactor |
代码或者功能重构 |
style |
仅修改样式,如缩进、分号、空格、制表符、换行符、引号、逗号、分号、冒号、圆括号、方括号、花括号、引号、注释、空行、缩进、换行符、制表符、空格、分号、逗号、分号、冒号、圆括号、方括号、花括号、引号、注释、空行、缩进、换行符、制表符、空格、分号、逗号、分号、冒号、圆括号、方括号 |
test |
添加或修改测试用例 |
revert |
撤销上一次提交 |
确有需要时可使用标准类型 refactor、test、build、style、revert,不要为了规避上述已有类型而新增近义类型。
Scope
- 默认省略;仓库历史大多数提交不使用 scope
- 仅在能显著澄清影响范围时添加,例如
fix(k8s): ... - 使用简短的小写名,例如
api、admin、blog、k8s、scheduler - 不要把文件名或过细的模块名作为 scope
Description
- 使用英文,延续仓库近期提交习惯
- 使用祈使语气和现在时,例如
add、fix、remove、adjust、rename - 冒号后使用小写字母开头,专有名词除外
- 描述结果和意图,不描述操作过程,不使用
update code、fix issue等模糊措辞 - 保持简洁,标题建议不超过 72 个字符,末尾不加句号
- 一条提交只表达一个逻辑变更;存在多个不相关变更时拆分提交
Body And Footer
- 简单变更不写正文,符合本仓库绝大多数历史提交
- 复杂变更可在空行后说明原因、关键行为和取舍,不重复标题
- 不编造 issue、PR 或作者信息
- 不添加任何 AI 署名或生成声明,包括
Co-authored-by、Generated-by、Assisted-by等;提交只保留开发者自身的 Git 作者信息 - 破坏性变更使用
type(scope)!:,并在 footer 写BREAKING CHANGE: ...
工作流程
1. 检查仓库状态
提交或生成消息前必须同时检查:
git status --short
git diff
git diff --staged
git log --oneline -10
识别暂存与未暂存变更、用户已有修改、生成文件和疑似敏感信息。不要修改、还原或覆盖并非当前任务产生的变更。
2. 确定提交边界
- 根据 diff 的实际行为选择 type,不能只根据文件路径猜测
- 将不相关变更拆成独立提交
- 如果无法判断哪些变更属于本次提交,先询问用户
- 若用户仅要求生成 commit message,不暂存文件、不运行
git commit
3. 验证变更
- 根据变更范围运行最小且充分的格式化、测试或构建命令
- Go 代码至少考虑
gofmt和相关go test;前端至少考虑对应应用的 lint 或 build - 验证失败时先修复当前任务导致的问题;不能修复时明确报告,不隐瞒失败
4. 暂存与提交
仅当用户明确要求创建提交时执行:
- 精确暂存本次提交涉及的文件,不使用
git add .、git add -A或git commit -a - 提交前再次检查
git diff --staged,确保没有无关文件、密钥或调试内容 - 使用非交互命令提交,例如
git commit -m "feat: add article search filters" - 需要正文时使用多个
-m参数,不打开交互式编辑器 - 不添加 AI 的 co-author、sign-off、工具名称、模型名称或其他归属信息
- 不使用
--amend、--no-verify或空提交,除非用户明确要求且风险可接受 - hook 失败时修复问题后创建新提交,不绕过 hook
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 · 133 lines · 41 tokens per session scan A 98b5e6ce6933
git-commit is a skill published in the GitHub repository iceymoss/go-hichat-api (41 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,402 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…