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 hanzhcn/laohan-skills --skill laohan-lupinggit clone --depth 1 https://github.com/hanzhcn/laohan-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/hanzhcn/laohan-skills/laohan-luping)<a href="https://agentmods.dev/skills/hanzhcn/laohan-skills/laohan-luping"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-luping/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/hanzhcn/laohan-skills/laohan-luping"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-luping.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 | $0.00087 | $0.02136 |
| Opus 5.5 | $0.00035 | $0.00854 |
| Sonnet 5.5 | $0.00017 | $0.00427 |
| Haiku 4.5 | $0.00009 | $0.00214 |
Grade A, and why
laohan-luping 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
录屏自动化：口播稿 → 录屏脚本 → MP4
边界（2026-09-20治理P2-20）：本工具不进入episode生产合同。episode内的录屏只响应⑨冻结的
LOCAL_CAPTURE请求（Prompt 08 / local-capture-mvp），无请求时为NOT_NEEDED；勿在episode上下文用本工具发起录屏。独立研究、demo或Jeffrey明确要求的自由录屏不受此限。
输入一篇口播稿（或录屏指示），自动生成 bash 录屏脚本。脚本编排 CLI 操作（tmux+Claude Code）和浏览器操作（Playwright headed），ffmpeg 录物理屏幕，输出 1080p MP4。
核心理念
口播稿即脚本蓝图。 每段口播对应一个屏幕操作（CLI 命令/浏览器导航/静态等待），从口播稿里提取出操作序列和时长，填入录制模板。
看到什么录什么。 ffmpeg 录物理屏幕，tmux 前台显示终端，Playwright headed 显示浏览器。两种"演员"按口播稿交替出场。
录屏是素材，不是生产。 录制过程中的临时文件全部自动清理，只保留最终 MP4。
工作流
1. 输入口播稿
接收用户提供的：
- 口播稿文件路径（
script.md） - 或录屏指示文件路径（
录屏指示.md） - 或直接描述要录制什么
如果用户提供了口播稿但没有录屏指示 → 根据口播稿内容自动推断每段对应的操作。 如果用户提供了录屏指示 → 直接用指示里的操作序列。
- 完成条件： 拿到完整的操作序列和每步时长
2. 解析口播稿→操作序列
从口播稿/录屏指示中提取。操作分为三种类型：
CLI 操作（tmux + Claude Code）：
| 口播段落 | 屏幕操作 | 脚本动作 |
|---|---|---|
| "说「抓今天的AI精选」" | 执行命令 | send_cmd "抓今天的AI精选" |
| "说「帮我写口播稿」" | 执行命令 | send_cmd "帮我写口播稿" |
| "展示 output/ 文件夹" | 查看命令 | send_cmd "ls output/" |
浏览器操作（Playwright headed）：
| 口播段落 | 屏幕操作 | 脚本动作 |
|---|---|---|
| "打开 GitHub 项目页" | 导航到 URL | browser_goto "https://github.com/..." |
| "看一下 README" | 页面滚动 | browser_scroll 500 |
| "点击安装文档" | 点击链接 | browser_click "a[href='docs']" |
| "展示项目截图" | 静态展示 | browser_wait 3000 |
静态操作（纯等待）：
| 口播段落 | 屏幕操作 | 脚本动作 |
|---|---|---|
| 开场白/过渡/结尾 | 静态画面 | sleep N |
提取规则：
-
引号里的内容（「」或""）→ 直接作为 send_cmd 的参数
-
提到 URL / GitHub / 网站 / 文档 → 浏览器操作
-
提到终端/命令/CLI → CLI 操作
-
纯叙述段落 → 按口播时长估算 sleep 秒数（正常语速约 3 字/秒）
-
CLI 命令需要等 Claude 完成的 → 加
wait_for_claude -
浏览器页面需要阅读时间的 → 加
browser_wait -
完成条件： 生成结构化的操作列表，每条含类型（cli/browser/static）、内容、等待方式、标签
3. 环境检测
which ffmpeg && which tmux && which node
ffmpeg -f avfoundation -list_devices true -i "" 2>&1 | grep "Capture screen"
node -e "require('playwright')" 2>/dev/null && echo "playwright OK" || echo "playwright missing"
- 缺工具 → 提示安装
- 多屏幕 → 让用户确认索引
- 缺 Playwright →
npm install playwright - 完成条件： 确认屏幕索引 + Playwright 可用（如需浏览器段）
What ships with it
4 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 Changed · +2 lines 667cb704270d
- 1mo ago First seen · 162 lines · 87 tokens per session scan A 91def4b2b063
laohan-luping is a skill published in the GitHub repository hanzhcn/laohan-skills (15 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 2,136 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
pentest-client-advanced
Advanced client-side attacks — CORS misconfiguration, WebSocket security, clickjacking, postMessage abuse, CSS injection, and browser storage vulnerabilities.
browser-extension-builder
Expert in building browser extensions that solve real problems - Chrome, Firefox, and cross-browser extensions. Covers extension architecture, manifest v3, content scripts, popup UIs, monetization strategies, and Chrome Web Store publishing. Use when: browser extension, chrome extension, firefox addon, extension…
browser-automation
Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns. This skill covers Playwright (recommended) and Puppeteer, with patterns for testing, scraping…
openclaw-browser-auto
A setup guide for connecting OpenClaw, an AI-agent platform, to a remote Chrome browser through CDP, a browser control interface. It covers Docker-hosted browsers and Browserless.io, a hosted browser service.
automation-browser-api-workflows
Class-level workflow for browser automation, API reverse-engineering, macOS UI automation, tmux/interactive CLI control, MCP tool calling, camera capture, and direct tool/API replacement of fragile UI flows. Use when asked to automate websites/apps, learn private site APIs from traffic, drive interactive CLIs, call…
api-learner
Workflow for learning site APIs via traffic capture and replacing browser automation with direct curl calls.