Borrowing it
Nothing to install: this file belongs to yibie/skills-manager. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/yibie/skills-manager/main/CLAUDE.mdgit clone --depth 1 https://github.com/yibie/skills-managerWrote 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/instructions/yibie/skills-manager/claude-md)<a href="https://agentmods.dev/instructions/yibie/skills-manager/claude-md"><img src="https://agentmods.dev/badge/instructions/yibie/skills-manager/claude-md/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/instructions/yibie/skills-manager/claude-md"><img src="https://agentmods.dev/badge/instructions/yibie/skills-manager/claude-md.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 | $0.00642 | $0.00642 |
| Opus 5 | $0.00321 | $0.00321 |
| Sonnet 5 | $0.00128 | $0.00128 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
skills-manager CLAUDE.md 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.
What it actually says
Skills Manager - Development Guide
TUI Engine: blessed
TUI (tui/) 使用 blessed 作为渲染引擎。
核心原则
- 让 blessed list 自己处理导航 — 设置
keys: true, vi: true,不要用screen.key('j')手动管理光标 - 监听
'select item'事件更新 detail — 不要自己维护selectedIndex - 全局快捷键检查焦点 — 在
screen.key()中用screen.focused !== target来限制作用域 - 异步更新只改 detail box — blessed 差分渲染确保不闪烁
参考文档
tui/docs/blessed-engine.md— blessed 渲染模型、List widget、键盘处理、滚动机制的详细说明
正确的 List 用法
// 创建 list 时启用内置导航
const list = blessed.list({
keys: true, // 方向键导航
vi: true, // j/k/g/G 等 vim 键
mouse: true, // 鼠标支持
style: { selected: { bg: 'blue', fg: 'white' } },
items: [...],
})
// 监听光标移动(不是手动管理 selectedIndex)
list.on('select item', (item, index) => {
updateDetail(index)
})
// 监听 Enter 确认
list.on('select', (item, index) => {
performAction(index)
})
list.focus()
不要做的事
- 不要
screen.key(['j'], () => { selectedIndex++; list.select(selectedIndex) })— 会和 list 内置处理冲突 - 不要 自己管理
selectedIndex变量 — 用(list as any).selected读取 - 不要 在光标移动时调用
render()以外的全量刷新 — list 的内置处理已包含screen.render()
弹窗模式
创建新的 blessed widget 作为弹窗,设置 parent: screen,调用 .focus() 抢占焦点。关闭时 .destroy() 并恢复原焦点。
项目结构
tui/
├── src/
│ ├── index.ts # 入口(blessed 版本)
│ ├── app-blessed.ts # 主应用
│ ├── services/ # 数据服务
│ │ ├── SkillStore.ts
│ │ ├── InstallService.ts
│ │ ├── DiscoverInstallService.ts
│ │ └── SkillsDirectoryService.ts
│ └── types.ts
├── docs/
│ └── blessed-engine.md # blessed 引擎参考文档
└── package.json
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 · 70 lines · 642 tokens per session scan A 93a6e0c74a47
skills-manager CLAUDE.md is an instructions file published in the GitHub repository yibie/skills-manager (440 stars, last pushed 1mo ago), licensed MIT. It adds 642 tokens to every session, about $0.0032 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.