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_visible-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_visible-en)<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw/browser_visible-en"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw/browser_visible-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_visible-en"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw/browser_visible-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 | $0.00075 | $0.00464 |
| Opus 5.5 | $0.00030 | $0.00186 |
| Sonnet 5.5 | $0.00015 | $0.00093 |
| Haiku 4.5 | $0.00007 | $0.00046 |
Grade A, and why
browser_visible 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.
What it actually says
Deprecated: This reference supports the stable
browserimplementation. hatch. Prefer the unifiedbrowsertool when experimental mode is enabled.
Browser Launch Modes
browser.start launch modes:
- Default: Playwright-managed, no debugging port
cdp_port=N: managed CDP, opens a local debugging port so other local tools can attach (see the browser_cdp skill)private_mode=true: same as the default, kept for backward compatibility
Parameter meanings:
headed: whether to display the browser windowprivate_mode: kept for backward compatibility; it no longer changes the launch mode
The two parameters are independent and can be freely combined.
Common Usage
Default launch:
{"action": "start"}
Open a visible window:
{"action": "start", "headed": true}
private_mode
Already the default behavior — do not set it. The parameter is kept only so that older calls keep working, and passing it together with cdp_port is rejected.
Notes
- The default is Playwright-managed with no debugging port
- The launch mode is entirely determined by the call parameters
- Managed CDP requires Chrome / Chromium / Edge to be installed locally
- When the user manually operates the visible browser, the idle timer may not be refreshed
private_modeis an explicit parameter for eachstartcall and is not persisted- If a browser is already running, you must
stopit and thenstartagain to switch launch modes or window visibility - Visible mode occupies the desktop and requires a graphical environment; it may not work on servers or headless environments
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 · 54 lines · 75 tokens per session scan A a26b245e6b45
browser_visible is a skill published in the GitHub repository agentscope-ai/QwenPaw (36,385 stars, last pushed yesterday), licensed Apache-2.0. It adds 75 tokens to every session and 464 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…