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-engit 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-en)<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw/browser_cdp-en"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw/browser_cdp-en/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-en"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw/browser_cdp-en.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 | $0.00070 | $0.01633 |
| Opus 5.5 | $0.00028 | $0.00653 |
| Sonnet 5.5 | $0.00014 | $0.00327 |
| Haiku 4.5 | $0.00007 | $0.00163 |
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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deprecated: This reference supports the stable
browserimplementation. hatch. Prefer the unifiedbrowsertool when experimental mode is enabled.
Browser CDP Reference
By default, browser opens no debugging port: the browser is managed directly by Playwright. This skill covers the cases where a CDP port is wanted on purpose.
This skill focuses on more "explicit" CDP usage:
- Scanning local CDP ports
- Connecting to an existing Chrome (
connect_cdp) - Explicitly specifying a
cdp_portwhen launching the browser - Sharing a single browser instance across multiple agents/tools
In other words:
- The default
startopens no debugging port, so users typically do not need to understand or be aware of CDP details - Only enter the scope of this skill when the user explicitly mentions "connect to an existing browser / scan ports / specify a port / share a browser"
Privacy Recommendation
The default
startexposes nothing — no debugging port is opened. Only passcdp_portwhen the user explicitly wants another local tool to attach, and warn about the exposure first.
Warning: One browser instance per workspace
Only one browser can be running or connected per workspace at a time. If a browser instance already exists, you must execute
stopfirst before switching to a new browser or a new CDP connection.
When to Use
Use this skill only when the user explicitly expresses one of the following intentions:
- "Connect to my already-open Chrome"
- "Scan for available CDP ports on this machine"
- "Launch the browser with a fixed debug port"
- "Let other agents/tools connect to this browser too"
- "Attach to the browser via the remote debugging port"
In the following cases, you should typically not use this skill:
- The user just says "open the browser"
- The user just says "open a visible window"
- The user does not mention sharing, ports, CDP, or remote debugging
In these cases, use the standard start, adding headed=true if needed — refer to browser_visible.
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 · 202 lines · 70 tokens per session scan A 5d320a9e2b69
browser_cdp is a skill published in the GitHub repository agentscope-ai/QwenPaw (36,385 stars, last pushed yesterday), licensed Apache-2.0. It adds 70 tokens to every session and 1,633 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…