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-xiazaigit 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-xiazai)<a href="https://agentmods.dev/skills/hanzhcn/laohan-skills/laohan-xiazai"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-xiazai/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-xiazai"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-xiazai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 110 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
- medium Data Exfiltration · line 205 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium MCP Rug Pull · line 32 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00443 | $0.07712 |
| Opus 5.5 | $0.00177 | $0.03085 |
| Sonnet 5.5 | $0.00089 | $0.01542 |
| Haiku 4.5 | $0.00044 | $0.00771 |
Grade B, and why
laohan-xiazai scanned grade B with 2 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 yesterday.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
> **Python 环境提示**：Debian/Ubuntu 系统 Python 有 PEP 668 锁，`pip3 install` 会被拒——统一改用 `pipx install <包>`（先 `pip3 install --user pipx`），CLI 工具进 `~/.local/bin` 等价可用。ffmpeg：macOS `brew install ffmpeg`；Debian/Ubuntu `sudo apt insta Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 网页正文：`curl -sL "https://r.jina.ai/<url>"`（Jina Reader，免 key 限速可用） How it starts
The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
从互联网拿内容
按平台选择正确方法，一步到位。先看平台路由表，再读对应 reference 文件。平台方法不行时，按品类降级链逐层深入——每层解决不同问题，能浅不深。
核心理念
能浅不深——先用最轻的方法（HTTP 请求），不行再加重量（浏览器渲染→反检测→AI 操作→手动控制）。成本递增，每层解决不同问题，不要跳层。
外部环境自举（External Bootstrap）
本 skill 在全新机器上：外部 AI 先按此清单装配依赖，再进入平台路由。装哪个取决于目标平台，不必全装。每项给安装命令 + 验证命令，装完跑验证确认可用。 Python 环境提示：Debian/Ubuntu 系统 Python 有 PEP 668 锁，
pip3 install会被拒——统一改用pipx install <包>（先pip3 install --user pipx），CLI 工具进~/.local/bin等价可用。ffmpeg：macOSbrew install ffmpeg；Debian/Ubuntusudo apt install ffmpeg；Winwinget install Gyan.FFmpeg。
| 层 | 工具 | 安装 | 验证 |
|---|---|---|---|
| 必装（通用下载/转码） | yt-dlp + ffmpeg | pip3 install -U "yt-dlp[default]"（YouTube 完整支持需完整依赖+JS runtime，见 官方 dependencies） |
yt-dlp --version && ffmpeg -version |
| 平台封装（30+ 平台主力） | opencli | npm install -g @jackwener/opencli（需 Node ≥20.18.1；Cookie 命令另需 Chrome 装扩展，见 opencli doctor 引导） |
opencli list |
| 搜索/阅读（13 平台统一入口） | agent-reach | pipx install git+https://github.com/Panniantong/agent-reach.git（⚠️ PyPI 同名包是别人的项目，必须从官方仓装） |
agent-reach doctor |
| AI 增强爬取（免费开源，批量页面→结构化） | Crawl4AI | pip3 install crawl4ai && crawl4ai-setup（LLM 结构化提取需另配模型——本地 Ollama 免费或云端 API 计费；纯 Markdown 提取不需模型） |
python3 -c "import crawl4ai" |
| 图集下载（Instagram/Twitter/Pixiv 等 100+ 站） | gallery-dl | pip3 install gallery-dl |
gallery-dl --version |
| AI 自主浏览器（未知页面探索） | browser-use | pip3 install browser-use，浏览器与模型配置按官方 quickstart |
python3 -c "import browser_use" |
| 反指纹浏览器（可选，硬反爬站） | Camoufox | pip3 install -U 'camoufox[geoip]' && python3 -m camoufox fetch（注意 shell 引号；代理场景配 geoip=True 才自动匹配地理位置指纹） |
python3 -c "import camoufox" |
本机专属工具说明：huashu-chrome MCP、Scrapling MCP、anysearch、web-access、douyin-session、dy-cli 是老韩本机配置，外部机器没有——降级链中遇到这些层时直接跳到下一层（外部等效：Scrapling→Crawl4AI/Camoufox，huashu-chrome→browser-use/Playwright，anysearch→DuckDuckGo/SearXNG）。
| 精确控制（确定性脚本） | Playwright | pip3 install playwright && playwright install chromium | playwright --version |
What ships with it
6 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.
- yesterday Changed 3657e03acbf4
- 4d ago Changed · +49 lines · +55 tokens per session scan A → B a06ece49606b
- 23d ago Changed · +28 tokens per session 4b798a365130
- 1mo ago First seen · 247 lines · 360 tokens per session scan A 3ed89182a16c
laohan-xiazai is a skill published in the GitHub repository hanzhcn/laohan-skills (15 stars, last pushed yesterday), licensed MIT. It adds 443 tokens to every session and 7,712 once invoked, about $0.0018 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). 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.