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/xcodethink/open-claude-code-skills/11npx skills add xcodethink/open-claude-code-skills --skill 11git clone --depth 1 https://github.com/xcodethink/open-claude-code-skillsWrote 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/11)<a href="https://agentmods.dev/skills/xcodethink/open-claude-code-skills/11"><img src="https://agentmods.dev/badge/skills/xcodethink/open-claude-code-skills/11.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 | $0.00235 | $0.01242 |
| Opus 5 | $0.00118 | $0.00621 |
| Sonnet 5 | $0.00047 | $0.00248 |
| Haiku 4.5 | $0.00023 | $0.00124 |
Grade A, and why
11-管理后台标准 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
管理后台统一标准
开发管理后台时,本目录包含所有需要的资料,按以下顺序使用:
🔴 核心原则:复制,不是重写
管理后台的通用模块 = 从 ProjectA 直接复制代码 + 只改业务数据。禁止从零重写。
📂 本目录结构
11-管理后台标准/
├── SKILL.md ← 你在这里(入口文档)
├── 新项目模板.md ← 🔴 新项目的 CLAUDE.md 模板(跨机器可移植)
├── 规范/ ← 所有管理后台规范文档
│ ├── 架构.md ← AdminApp 主容器、路由、骨架屏
│ ├── 后端.md ← 认证/设备指纹/流量/API用量/2FA/Cron
│ ├── 数据库.md ← 标准表结构
│ ├── API层.md ← adminApi.ts 封装
│ ├── 国际化.md ← adminLabels.ts 双语标签
│ ├── 通用功能模块.md ← 🔴 核心:模块清单 + 验收清单 + 跨项目同步
│ ├── API密钥管理.md ← Key 管理全栈方案
│ ├── Safari兼容.md ← 浏览器兼容修复
│ └── 视觉交互规范.md ← 🔴 视觉精致度标准(间距/字体/颜色/动画/骨架屏/空态/深色模式)
├── UI组件/ ← 共享 UI 组件规范
│ ├── 侧边栏导航.md
│ ├── 数据表格.md
│ ├── 统计卡片.md
│ ├── 图表组件.md
│ ├── 表单组件.md
│ ├── 弹窗和抽屉.md
│ └── 状态标签.md
└── 模板代码/ ← 可直接复制的模板代码
├── README.md ← 模板使用说明
├── PATTERNS.md ← 代码模式
├── DESIGN.md ← 设计规范
├── components/admin/ ← 前端组件模板
│ ├── AdminApp.tsx
│ ├── AdminSidebar.tsx
│ ├── AdminHeader.tsx
│ ├── AdminLogin.tsx
│ ├── shared/ ← 8 个共享 UI 组件
│ └── tabs/ ← 14 个通用 Tab 模板(✅ 8 必选 + 📦 6 可选)
├── layouts/AdminLayout.astro
├── lib/ ← API 层模板
│ ├── adminApi.ts
│ ├── adminLabels.ts
│ └── lazyWithRetry.ts
└── pages/admin.astro
🔴 开发步骤
第 1 步:复制模板代码
从 模板代码/ 目录复制所有文件到新项目对应位置,只改项目名和导航项。
第 2 步:查阅规范文档
- 不确定架构时 → 读
规范/架构.md - 不确定后端时 → 读
规范/后端.md+规范/数据库.md - 不确定功能模块时 → 读
规范/通用功能模块.md
第 3 步:查阅 UI 组件规范
需要特定组件的详细用法时,读 UI组件/ 下对应文档。
第 4 步:新项目配置
把 新项目模板.md 里的内容加入项目的 CLAUDE.md,确保跨机器可移植。
🔴 跨机器使用
方案 A:同步 skills 目录(推荐)
将 ~/.claude/skills/ 做为 Git 仓库管理,新机器 clone 即可。
方案 B:项目自带规范
把 新项目模板.md 的内容写入项目的 CLAUDE.md,这样即使没有 skills 目录,Claude Code 也知道从哪里复制代码。
⚠️ 与组件规范的关系
本目录是从 03-组件规范/web/ 独立出来的完整版。管理后台开发只需读本目录,不需要再去 03-组件规范。
What ships with it
53 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.
- agents/openai.yaml 880 B
- SKILL.en.md 4.5 KB
- UI组件/侧边栏导航.md 8.2 KB
- UI组件/图表组件.md 8.8 KB
- UI组件/弹窗和抽屉.md 8.1 KB
- UI组件/数据表格.md 7.8 KB
- UI组件/状态标签.md 4.9 KB
- UI组件/统计卡片.md 5.0 KB
- UI组件/表单组件.md 9.6 KB
- 新项目模板.md 5.4 KB
- 模板代码/components/admin/AdminApp.tsx 9.6 KB
- 模板代码/components/admin/AdminHeader.tsx 2.0 KB
- 模板代码/components/admin/AdminLogin.tsx 4.1 KB
- 模板代码/components/admin/AdminSidebar.tsx 5.5 KB
- 模板代码/components/admin/shared/DataTable.tsx 2.3 KB
- 模板代码/components/admin/shared/HorizontalBar.tsx 1.7 KB
- 模板代码/components/admin/shared/LineChart.tsx 9.2 KB
- 模板代码/components/admin/shared/MiniChart.tsx 3.2 KB
- 模板代码/components/admin/shared/Modal.tsx 1.4 KB
- 模板代码/components/admin/shared/Pagination.tsx 1.4 KB
- 模板代码/components/admin/shared/StatCard.tsx 996 B
- 模板代码/components/admin/shared/StatusBadge.tsx 1.2 KB
- 模板代码/components/admin/tabs/AnalyticsTab.tsx 13 KB
- 模板代码/components/admin/tabs/ApiAlertsTab.tsx 26 KB
- 模板代码/components/admin/tabs/ApiHealthTab.tsx 4.8 KB
- 模板代码/components/admin/tabs/ApiServicesTab.tsx 29 KB
- 模板代码/components/admin/tabs/BlogTab.tsx 30 KB
- 模板代码/components/admin/tabs/FeedbackTab.tsx 7.2 KB
- 模板代码/components/admin/tabs/GoogleAnalyticsTab.tsx 14 KB
- 模板代码/components/admin/tabs/OrdersTab.tsx 13 KB
- 模板代码/components/admin/tabs/OverviewTab.tsx 6.9 KB
- 模板代码/components/admin/tabs/RenewalsTab.tsx 32 KB
- 模板代码/components/admin/tabs/RevenueTab.tsx 3.0 KB
- 模板代码/components/admin/tabs/SecurityTab.tsx 11 KB
- 模板代码/components/admin/tabs/UsersTab.tsx 9.7 KB
- 模板代码/components/admin/tabs/WebhooksTab.tsx 4.8 KB
- 模板代码/DESIGN.md 5.4 KB
- 模板代码/layouts/AdminLayout.astro 626 B
- 模板代码/lib/adminApi.ts 8.6 KB runs code
- 模板代码/lib/adminLabels.ts 7.1 KB runs code
- 模板代码/lib/lazyWithRetry.ts 1.3 KB runs code
- 模板代码/pages/admin.astro 314 B
- 模板代码/PATTERNS.md 17 KB
- 模板代码/README.md 12 KB
- 规范/API密钥管理.md 16 KB
- 规范/API层.md 9.9 KB
- 规范/Safari兼容.md 3.1 KB
- 规范/后端.md 44 KB
- 规范/国际化.md 5.7 KB
- 规范/数据库.md 18 KB
- 规范/架构.md 23 KB
- 规范/视觉交互规范.md 22 KB
- 规范/通用功能模块.md 36 KB
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 · 90 lines · 235 tokens per session scan A e78bb1610f53
11-管理后台标准 is a skill published in the GitHub repository xcodethink/open-claude-code-skills (2 stars, last pushed 29d ago), licensed MIT. It adds 235 tokens to every session and 1,242 once invoked, about $0.0012 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
om-backend-ui-design
Design and implement consistent, production-grade backend/backoffice interfaces using the @open-mercato/ui component library. Use this skill when building admin pages, CRUD interfaces, data tables, forms, detail pages, or any backoffice UI components. Ensures visual consistency and UX patterns across all application…
ss-studio
Turn a product brief and optional references into three distinct creative directions, a human-selected StyleSeed interaction plan, generated image/video asset jobs, a working UI prototype, and a verified prototype-first showcase reel. Use for client concepts, app interaction exploration, trendy but coherent UI…
ss-copy
Generate UX microcopy (button labels, error messages, empty states, toasts) following a casual-but-polite voice and tone.
moai-domain-frontend
Frontend development specialist covering React 19, Next.js 16, Vue 3.5, and modern UI/UX patterns with component architecture. Use when building web UIs, implementing components, optimizing frontend performance, or integrating state management.
design-director
Используй только внутри активного Codex Project Autopilot-проекта, когда уже выбрана проектная фаза и нужен design direction по плану автопилота.
ss-review
Review UI code for design system compliance, accessibility, and best practices.