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-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_visible-zh)<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw/browser_visible-zh"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw/browser_visible-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_visible-zh"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw/browser_visible-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 | $0.00108 | $0.01053 |
| Opus 5 | $0.00054 | $0.00526 |
| Sonnet 5 | $0.00022 | $0.00211 |
| Haiku 4.5 | $0.00011 | $0.00105 |
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 12d 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
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。
浏览器启动模式
browser.start 的启动方式:
- 默认:Playwright 直接管理,不开放调试端口
cdp_port=N:managed CDP,开放本地调试端口供其他本地工具附加(详见 browser_cdp skill)private_mode=true:与默认相同,保留用于兼容
参数含义:
headed:是否显示浏览器窗口private_mode:保留用于兼容,不再改变启动方式browser_args:额外的 Chromium 启动参数(字符串),多个参数用空格分隔。适用于所有启动路径(headless、headed、managed CDP)。例如"--incognito"启用隐身模式,"--proxy-server=http://127.0.0.1:7890"设置代理。默认空字符串(无额外参数)。executable_path:自定义浏览器可执行文件路径(字符串)。设置后覆盖系统默认浏览器检测,可指定任意基于 Chromium 的浏览器。例如"C:\\Program Files\\Google\\Chrome\\Application\\chrome.exe"。仅允许包含已知浏览器关键词(chrome、chromium、edge、firefox、brave 等)的可执行文件,且文件必须存在。默认空字符串(使用系统默认)。
以上参数互不影响,可自由组合。
常见用法
默认启动:
{"action": "start"}
打开可见窗口:
{"action": "start", "headed": true}
隐身模式:
{"action": "start", "headed": true, "browser_args": "--incognito"}
指定浏览器路径 + 设置代理:
{"action": "start", "headed": true, "browser_args": "--proxy-server=http://127.0.0.1:7890", "executable_path": "C:\\Program Files\\Google\\Chrome\\Application\\chrome.exe"}
private_mode
已是默认行为,无需设置。该参数仅为兼容旧调用而保留,与 cdp_port 同时传入会被拒绝。
什么时候用 browser_args
当用户需要传入 Chromium 原生启动参数时使用,常见场景:
- 隐身/无痕模式(
--incognito、--inprivate) - 设置代理(
--proxy-server) - 指定窗口大小(
--window-size=1920,1080) - 禁用 GPU(
--disable-gpu) - 加载扩展(
--load-extension=/path/to/ext)
参数使用 shell 风格的空格分隔,在 Windows 上会自动处理路径中的反斜杠。
什么时候用 executable_path
当用户需要使用非系统默认的浏览器时使用,常见场景:
- 系统默认是 Chrome,但用户想用 Edge
- 安装了多个浏览器,想指定某一个
- 使用便携版浏览器
注意:executable_path 只接受包含已知浏览器关键词(chrome、chromium、edge、firefox、brave、vivaldi、opera、360se、yandex、tor)的可执行文件,且路径必须指向一个真实存在的文件。
注意
- 默认由 Playwright 直接管理,不开放调试端口
- 启动方式完全由调用参数决定
- managed CDP 依赖本机存在 Chrome / Chromium / Edge
- 用户手动操作可见浏览器时,不一定会刷新 idle 计时
private_mode、browser_args、executable_path都是每次start的显式参数,不会持久保存- 若当前已有浏览器在运行,需要先
stop再重新start,才能切换启动方式、窗口可见性或启动参数。 - 可见模式会占用桌面并需要图形环境,服务器或无图形环境可能无法使用。
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.
- 12d ago First seen · 87 lines · 108 tokens per session scan A 6df804888692
browser_visible is a skill published in the GitHub repository agentscope-ai/QwenPaw (34,741 stars, last pushed yesterday), licensed Apache-2.0. It adds 108 tokens to every session and 1,053 once invoked, about $0.0005 per session on Opus 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) 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…
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…
browser_cdp
A guide for connecting browser-control tools to an existing Chrome session through its remote debugging interface. It explains scanning ports, attaching to a browser, choosing a port, sharing a browser, and switching to a more private control mode.
browser_visible
A guide to browseruse launch settings for Chromium-based browsers. It covers visible windows, private control, extra browser start options such as incognito mode or a proxy, and choosing a browser executable path.
browser_visible
Use this skill when the user needs to control the browser launch mode for browseruse. By default, browseruse launches the local Chrome/Chromium using managed CDP; headed controls whether the window is visible, and privatemode controls whether CDP is disabled in favor of Playwright.