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/southliu/south-admin-react/init-projectnpx skills add southliu/south-admin-react --skill init-projectgit clone --depth 1 https://github.com/southliu/south-admin-reactWrote 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/southliu/south-admin-react/init-project)<a href="https://agentmods.dev/skills/southliu/south-admin-react/init-project"><img src="https://agentmods.dev/badge/skills/southliu/south-admin-react/init-project.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 | $0.00083 | $0.00944 |
| Opus 5 | $0.00042 | $0.00472 |
| Sonnet 5 | $0.00017 | $0.00189 |
| Haiku 4.5 | $0.00008 | $0.00094 |
Grade A, and why
init-project 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 4d 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.
What it actually says
init-project
Description
初始化项目，丢弃模板自带的示例内容。该技能会调用 .claude/skills/init-project/scripts/ 下的 Python 清理脚本，删除以下目标并连带清理代码中的引用：
- 页面：
src/pages/demo/、src/pages/content/ - 组件：
src/components/Github/ - 接口：
src/servers/content/ - 静态菜单：
src/menus/demo.ts及src/menus/index.ts中的 demo 引用 - 国际化：
src/locales/zh/content.ts、src/locales/en/content.ts
同时清理以下代码引用：
src/layouts/components/Header.tsx：删除import Github from '@/components/Github';与<Github />标签src/menus/index.ts：删除import { demo } from './demo';与...(demo as SideMenu[])
Instructions
1. 执行清理脚本
调用 Python 脚本完成清理，必须先做 dry-run 预览，再确认删除：
# 1) dry-run 预览（不删除任何文件，仅打印将要删除的文件和将要修改的引用）
python .claude/skills/init-project/scripts/cleanup.py --dry-run
# 2) 确认无误后，真正执行删除
python .claude/skills/init-project/scripts/cleanup.py
或使用包装脚本（Windows 下推荐）：
bash .claude/skills/init-project/scripts/run.sh --dry-run # 预览
bash .claude/skills/init-project/scripts/run.sh # 执行
2. 确认流程（重要）
- 先运行
--dry-run，将脚本输出的「待删除文件清单」和「待修改引用清单」展示给用户。 - 明确询问用户是否确认执行删除。
- 用户确认后再运行不带
--dry-run的命令。 - 执行完成后，建议运行
pnpm lint和pnpm dev验证项目可正常构建运行。
3. 脚本行为说明
脚本（cleanup.py）会：
- 校验项目根目录（默认当前工作目录，可通过
--root <path>指定）。 - 计算所有待删除的文件/目录（仅删除存在的）。
- 计算所有待修改的引用文件（按精确字符串匹配替换）。
--dry-run模式下只输出计划，不写盘；非 dry-run 模式下执行删除与替换，并跳过已不存在的目标。- 仅做精确字符串替换，不会误伤业务代码；替换前会检查目标字符串是否存在。
4. 替换规则（精确匹配）
| 文件 | 替换内容 |
|---|---|
src/layouts/components/Header.tsx |
删除 import Github from '@/components/Github';\n 整行，删除 <Github />\n 整行 |
src/menus/index.ts |
删除 import { demo } from './demo';\n 整行，将 ...(demo as SideMenu[]),\n 整行删除 |
注：脚本使用精确字符串匹配。如果上述文件已被人为修改导致字符串不再精确匹配，脚本会跳过该替换并在输出中提示「未找到匹配」，此时需人工检查。
5. 安全检查
- 脚本默认不会删除脚本自身所在目录之外的任意文件，仅处理上述明确的目标。
- 所有路径均相对项目根目录计算，不会跨项目删除。
- 若目标已被删除（重复执行），脚本会安全跳过。
What ships with it
3 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.
- 4d ago First seen · 73 lines · 83 tokens per session scan A cdd8fc0a41d6
init-project is a skill published in the GitHub repository southliu/south-admin-react (578 stars, last pushed 13d ago), licensed MIT. It adds 83 tokens to every session and 944 once invoked, about $0.0004 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
antd
Use when the user's task involves Ant Design (antd) — writing antd components, debugging antd issues, querying antd APIs/props/tokens/demos, migrating between antd versions, or analyzing antd usage in a project. Triggers on antd-related code, imports from 'antd', or explicit antd questions.
v3-create-crud
创建增删改查（CRUD）页面，基于 Element Plus 组件库，包含表格、搜索、分页、新增/编辑弹窗、删除确认等功能。当用户提到以下任何场景时都应触发：创建管理页面、创建列表页、创建表格页。即使用户没有明确说 CRUD，只要意图是创建带表格和表单操作的后台页面就应该使用此 Skill。使用时需提供模块名称和字段信息。.
v3-upsert-route
根据用户提供的路由信息，在 src/router/index.ts 中生成或更新路由配置。.
v3-upsert-store
创建或更新全局状态（Store）。当用户提到以下任何场景时都应触发：新建状态管理、新增 Pinia Store、给 Store 加字段。即使用户没有明确说 Store，只要意图是和状态管理器有关就应该使用此 Skill。使用时需提供 Store 名称、State 字段和 Actions 描述。.
v3-use-composables
项目内置组合式函数使用教程，涵盖设备检测、异步下拉、全屏加载、分页、路由监听、主题切换、动态标题、水印等组合式函数。当用户提到以下任何场景时都应触发：使用组合式函数、调用 Composables、判断设备类型、异步加载下拉选项、全屏 Loading、分页逻辑、监听路由变化、切换主题、设置页面标题、添加水印。即使用户没有明确说 Composables，只要意图是使用项目内置的组合式函数就应该使用此 Skill。.
v3-use-utils
项目内置工具函数使用教程，涵盖验证、日期格式化、CSS 变量、权限判断、本地存储等工具。当用户提到以下任何场景时都应触发：使用工具函数、调用 utils、格式化日期、判断权限、操作 localStorage、获取/设置 CSS 变量、验证数据类型、判断外链、获取/存储 Token。即使用户没有明确说 Utils，只要意图是使用项目内置的通用工具函数就应该使用此 Skill。.