QwenPaw is a personal AI assistant that runs on a local machine or in the cloud and connects to multiple chat applications. It provides memory, file workspaces, multiple agents, skills, plugins, and integrations with language-model providers and external tools. The catalogue entries are skills that extend its capabilities.
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 agentscope-ai/QwenPaw --skill browser_cdp-zhgit clone --depth 1 https://github.com/agentscope-ai/QwenPawWrote 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/agentscope-ai/qwenpaw/browser_cdp-zh)<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw/browser_cdp-zh"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw/browser_cdp-zh/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/agentscope-ai/qwenpaw/browser_cdp-zh"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw/browser_cdp-zh.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 | $0.00085 | $0.01765 |
| Opus 5.5 | $0.00034 | $0.00706 |
| Sonnet 5.5 | $0.00017 | $0.00353 |
| Haiku 4.5 | $0.00009 | $0.00177 |
Grade A, and why
browser_cdp 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
已弃用: 此参考服务于稳定的
browser实现。启用实验模式时,请优先使用统一的browser工具。
浏览器 CDP 使用参考
browser 默认不开放调试端口,浏览器由 Playwright 直接管理。本 skill 关注的是有意需要 CDP 端口的场景。
本 skill 关注的是更“显式”的 CDP 用法:
- 扫描本地 CDP 端口
- 连接已有 Chrome(
connect_cdp) - 显式指定
cdp_port启动浏览器 - 让多个 agent / 工具共享同一个浏览器实例
也就是说:
- 普通
start不开放调试端口,通常不需要用户理解或感知 CDP 细节 - 只有在用户明确提出“连接现有浏览器 / 扫描端口 / 指定端口 / 共享浏览器”时,才应进入本 skill 的语义范围
隐私建议
默认
start本身不暴露任何东西——不会开放调试端口。只有用户明确希望其他本地工具附加时才传cdp_port,并应先提示暴露风险。
⚠️ 单 workspace 单浏览器实例
同一 workspace 同时只能运行或连接一个浏览器。若当前已有浏览器实例,必须先执行
stop,再切换到新的浏览器或新的 CDP 连接。
何时使用
仅在用户明确表达以下意图时使用本 skill:
- “连接到我已经打开的 Chrome”
- “扫描一下本机有哪些 CDP 端口可用”
- “用固定调试端口启动浏览器”
- “让别的 agent / 工具也能连到这个浏览器”
- “通过远程调试端口附着到浏览器”
以下情况通常不要进入本 skill:
- 用户只是说“打开浏览器”
- 用户只是说“开一个可见窗口”
- 用户没有提到共享、端口、CDP、远程调试
这些情况通常直接使用普通 start,必要时加 headed=true,参考 browser_visible 即可。
场景一:扫描本地 CDP 端口
默认扫描端口范围 9000–10000:
{"action": "list_cdp_targets"}
指定单个端口:
{"action": "list_cdp_targets", "port": 9222}
自定义扫描范围:
{"action": "list_cdp_targets", "port_min": 8000, "port_max": 12000}
适用场景:
- 用户已经手动启动了带远程调试端口的 Chrome
- 你不知道具体端口,先扫描确认
- 需要在连接前确认本机有哪些可附着目标
场景二:连接已有 Chrome
连接已存在的 CDP 端点:
{"action": "connect_cdp", "cdp_url": "http://localhost:9222"}
特点:
- 连接成功后,可以继续使用
open、snapshot、click、type等常规操作 - 这是附着到外部浏览器,不是 QwenPaw 自己启动的新进程
stop时只断开连接,不会关闭外部浏览器- 当前也受 idle auto-stop 管理,但 external CDP 的 auto-stop 语义是“自动断开,不关闭外部浏览器”
适用场景:
- 用户已经打开自己的 Chrome,并希望 agent 直接接管
- 需要附着到用户已有登录态 / 已打开标签页
场景三:显式指定 cdp_port 启动
如果用户明确要求使用固定端口,或需要把端点提供给其他工具,可以在 start 时指定 cdp_port:
{"action": "start", "cdp_port": 9222}
如需同时打开可见窗口:
{"action": "start", "headed": true, "cdp_port": 9222}
当前行为说明:
- 如果显式指定的
cdp_port已被占用,会直接报错,不会强行复用 - 如果不指定
cdp_port,则完全不开放端口,也不会自动挑选端口 - 显式指定端口时仍存在极小 race window:在“检测端口空闲”和“Chrome 真正绑定端口”之间理论上可能被别的进程抢占;当前失败时会清理并报错,但不会自动重试
因此:
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 First seen · 201 lines · 85 tokens per session scan A b754fab884b2
browser_cdp is a skill published in the GitHub repository agentscope-ai/QwenPaw (36,200 stars, last pushed 2d ago), licensed Apache-2.0. It adds 85 tokens to every session and 1,765 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
browser-setup
A setup guide for connecting Clacky's browser tool to Chrome or Edge. It supports macOS, Linux, and Windows installations used through WSL, and stores the connection settings in a configuration file.
channel-manager
Configure IM platform channels (Feishu, WeCom, Weixin, Discord, Telegram, DingTalk, QQ) for openclacky. Uses browser automation for navigation; guides the user to paste credentials and perform UI steps. Trigger on: "channel setup", "setup feishu", "setup wecom", "setup weixin", "setup wechat", "setup discord", "setup…
playwright-skill
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions…
demo
Record a demo video of a web app feature or flow on a real desktop (Docker, Xvfb, XFCE, real X cursor), producing an mp4 plus a click/hover/scroll/type telemetry file. Takes a flow description, an existing demo name or path, or init. Use when the user says "record a demo of the checkout", "gravar um demo dessa…
chrome-devtools
Browser debugging, performance profiling, and automation via Chrome DevTools MCP. Use when user says "debug this page", "take a screenshot", "check network requests", "profile performance", "inspect console errors", or "analyze page load". Do NOT use for full E2E test suites (use playwright-skill) or non-browser…
browser_cdp
Use this skill when the user explicitly wants to connect to a running Chrome browser, scan local CDP ports, specify a cdpport, or share a single browser across multiple agents/tools. By default, browseruse already launches the browser using managed CDP; if the user does not want to expose browser history, cookies, or…