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 skills add zhuanggenhua/BoardGame --skill git-operationsgit clone --depth 1 https://github.com/zhuanggenhua/BoardGameWrote 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/zhuanggenhua/boardgame/git-operations)<a href="https://agentmods.dev/skills/zhuanggenhua/boardgame/git-operations"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/git-operations/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zhuanggenhua/boardgame/git-operations"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/git-operations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.02961 |
| Opus 5 | $0.00022 | $0.01481 |
| Sonnet 5 | $0.00009 | $0.00592 |
| Haiku 4.5 | $0.00004 | $0.00296 |
Grade A, and why
git-operations 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 9d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git 操作 Skill
本 skill 只规定本项目里的 Git 操作边界。根 AGENTS.md 保留不可越过的红线;复杂提交、推送、PR、worktree 和 merge 细则以本文为准。
触发
用户要求以下动作时使用:
git status、diff、commit、push。- “检查一下没问题就提交 / 看下再推”。
- 同步
main、处理 pre-push、远端失败。 - PR、merge、fork、worktree、跨仓库写回。
基本原则
- 默认工作区可能是脏的,陌生改动先判断影响;无关就绕开,不顺手清。
- 不擅自
stash、restore、checkout --、clean、reset、rebase、revert。 - 不擅自创建、切换、删除分支或 worktree。
- Git 操作只处理用户当前授权目标,不自动升级成同步主线、修 bug、跑专项验证或整理全仓。
- 需要用户判断时先说现实含义,再给代码证据;不要只甩测试名、字段名或错误码。
看改动
日常审查顺序:
git status --short --branchgit diff --stat- 按目标读取关键文件 diff
审查时先把改动分类:用户可见行为、业务规则、测试/mock/fixture、生成物/evidence、文档规范、纯格式。拿不准、会恢复旧行为、触及用户刚修链路、改生产逻辑、改测试期望、影响 E2E 证据或合并裁定时,先上报现实含义和风险,不直接吞进提交。
提交
默认只提交本轮明确范围内的改动。
用户说“都提交 / 全修改 / 所有修改 / 全部改动”时,解释为审查当前仓库内已暂存、未暂存和未跟踪文件;不包含 ignored 文件。
提交规则:
git commit -m默认中文,标题写清业务对象和动作,不能写“修复问题 / 更新代码”。- 大提交用中文多行消息,覆盖主要文件簇、行为变化、测试/evidence 和用户点名事项。
- 提交消息必须来自真实 diff 审查;关键改动映射不上消息时,先继续审查。
- 提交前发现待提交对象超过 10MB,先判断是否应进仓库;诊断、trace、视频、临时 evidence、构建产物、日志和压缩包默认不提交。超过 50MB 需强理由;超过 100MB 视为 GitHub 推送硬阻塞。
- 涉及 i18n 或可见文案时,首次提交前默认跑
npm run i18n:check或等价最小检查。
提交切线:
- 当目标是“检查后提交 / 提交后 push”时,以首次提交前完成的审查和暂存范围作为本次提交切线。
git commit成功后新出现的未跟踪、截图、测试输出、后台产物或并发改动,默认不纳入本次提交。- 若后续 push 的 hook 失败且必须修改当前已提交内容才能通过,才回到门禁修复路径。
推送
目标涉及 push 时,默认先 git fetch --prune origin。fetch 只更新远端跟踪信息,不等于授权 pull、merge、rebase 或 stash。
fetch 后:
- 只是
ahead N:继续推送当前提交。 - 出现
behind或ahead + behind:不得自动 pull / merge / rebase / stash;说明远端已有新提交,让用户选择合并主线继续当前 PR、从最新主线重开、或暂缓同步。 - 用户当轮已明确要求“处理远端更新后继续推 / 同步后再推 / 合并远端再推 / 改到能 push”时,先锁定合并方向、工作区归属和双边范围,再推进。
push 失败先分网络/协议、hook、真实测试失败、权限失败。GitHub 403 / Permission denied / Write access denied 通常表示不能直推上游主仓;贡献代码默认切 fork + PR,而不是索要上游写权限。
绕过门禁、guard 或预算限制不是默认动作;没有用户当轮明确允许,不使用 --no-verify 或 bypass 环境变量。
“检查后提交/推”的动作上限
“检查没问题 / 看下再提交 / 看下再推”默认是静态审查后 Git 动作,不等于主动跑测试,也不等于授权修复。
即使 diff 含 UI,也不得自动启动 UI 审计、截图、Playwright、E2E、构建、lint 或 typecheck。只有用户点名、Git hook 自动触发,或静态审查发现需要机器确认的具体风险,才追加命令。
如果静态审查、hook 或生成脚本暴露需要编辑代码的问题:
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.
- 9d ago First seen · 199 lines · 43 tokens per session scan A af435c31cb80
git-operations is a skill published in the GitHub repository zhuanggenhua/BoardGame (22 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 2,961 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
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.