Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/xcodethink/open-claude-code-skillsnpx agentmods add skills/xcodethink/open-claude-code-skills/18-gitWrote 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/xcodethink/open-claude-code-skills/18-git)<a href="https://agentmods.dev/skills/xcodethink/open-claude-code-skills/18-git"><img src="https://agentmods.dev/badge/skills/xcodethink/open-claude-code-skills/18-git/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/xcodethink/open-claude-code-skills/18-git"><img src="https://agentmods.dev/badge/skills/xcodethink/open-claude-code-skills/18-git.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00269 | $0.03743 |
| Opus 5.5 | $0.00108 | $0.01497 |
| Sonnet 5.5 | $0.00054 | $0.00749 |
| Haiku 4.5 | $0.00027 | $0.00374 |
Grade A, and why
18-Git仓与安全 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 1mo 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git 仓库与安全规范
通用 skill — 所有项目的 Git 仓库分层、信息分级、防泄露规范。 与 17-项目目录标准 配套使用。 与 16-开源发布 互补：本 skill 管"日常 + 闭源", 16 管"对外开源发布"。
4 大执行 checklist（按 tier 分）
本 SKILL.md 是总览 — 具体每个 tier 的可执行 checklist 在子文件：
| Tier | 子文件 | 触发场景 |
|---|---|---|
| 本地建设 | 01-本地仓库建设标准.md |
新项目 Day 0 / 每次 commit / 每周维护 / 每季 token 轮换 |
| T1 personal push | 02-私人仓库推送标准.md |
personal private 仓 push 前 / 团队加入触发升级 / 误推 secret 应急 |
| T2 team push | 03-团队仓库推送标准.md |
付费 Org private 仓 push 前 / PR 流程 / 离职 access 撤销 |
| T2 派生镜像 | 03b-派生镜像团队仓标准.md |
个人账号 <project>-team 仓（不开 Org）/ 加外部协作者 / origin→team 过滤推送 / 审计必扫历史 blob |
| T3 open source | 04-开源仓库推送标准.md |
公开仓 release / T2→T3 promotion / 误发开源应急（联用 Skill 16） |
强制阅读顺序：先读本 SKILL.md（理解 4 级分级 + T0-T3 仓库分层），再按当前场景读对应子文件。
Lifecycle 决策树（避免过度工程化）
新项目要建仓
│
▼
团队人数 ≥ 2？或即将加入？
/ \
NO YES
│ │
▼ ▼
[T1 personal lab] [直接 T2 team org]
单人快速干活 需 GitHub Pro/Team plan
│
├─ 读 17 + 18 sub 01（建结构 + 安全配置）
├─ 读 18 sub 02（每次 push checklist）
└─ 不读 / 不需要 sub 03 / sub 04
│
▼
团队第 2 人加入触发？
/ \
NO YES
│ │
▼ ▼
留 T1 升级到 T2
├─ 创建 GitHub org
├─ 升级 plan（branch protection 解锁）
├─ T1→T2 promote 内容（用 promote.sh）
├─ 团队 invite 到 T2，不 invite T1
└─ 读 18 sub 03
│
▼
要开源 SDK / CLI？
/ \
NO YES
│ │
▼ ▼
T3 不启用 启用 T3
├─ 决策走 D-Legal-04 流程
├─ 读 18 sub 04 + Skill 16 全套
├─ Pre-publish 9 步审计强制
└─ T2→T3 单向 promote（不双向 sync）
What ships with it
9 files 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.
- 1mo ago First seen · 205 lines · 269 tokens per session scan A 4e2e7466f08b
18-Git仓与安全 is a skill published in the GitHub repository xcodethink/open-claude-code-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 269 tokens to every session and 3,743 once invoked, about $0.0011 per session on Opus 5.5. 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
git-commit-integrity
Ensures every commit in a series is what it claims to be — a working, gate-passing snapshot in isolation, not just a slice of a working directory that happened to pass while other changes sat nearby. Covers verifying commit history after the fact, designing pre-commit hooks that check the commit rather than the…
workflow-solo
Single-agent feature pipeline with adaptive complexity. User-invoked entry point via /workflow-solo; not for autonomous or subagent use.
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
prs-awaiting-author
List open pull requests where the ball is in the author's court: CI is failing, review comments are unaddressed, or a maintainer question is awaiting the author's reply. Use when the user wants to see PRs awaiting author action.