browser_cdp

browser_cdp is a skill for Claude Code, Codex from agentscope-ai/QwenPaw. It costs 85 tokens per session (1,765 once invoked), scanned A, original, Apache-2.0.

Browser connection controls for finding local debugging ports, attaching to an already running Chrome browser, or sharing one browser between tools.

In plain words
What is it for?
Use it to scan for local CDP targets, connect to an existing Chrome, start a browser on a chosen debugging port, or share one browser instance.
Why use it?
It removes the need to start a separate browser when another tool or agent must use the same session. It also makes explicit browser connections and their exposure easier to manage.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for qwenpaw. Also seen: built for qwenpaw.

Good fit Use it to scan for local CDP targets, connect to an existing Chrome, start a browser on a chosen debugging port, or share one browser instance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agentscope-ai/qwenpaw/browser_cdp-zh
About the project

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.

agentscope-ai/QwenPaw · 34,741 stars · on GitHub · qwenpaw.agentscope.io

Install

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.

Any agent
npx skills add agentscope-ai/QwenPaw --skill browser_cdp-zh
Clone the repo
git clone --depth 1 https://github.com/agentscope-ai/QwenPaw

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for browser_cdp

README.md
[![agentmods](https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw/browser_cdp-zh/github.svg)](https://agentmods.dev/skills/agentscope-ai/qwenpaw/browser_cdp-zh)
Your own site
<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.

agentmods 80×15 button for browser_cdp

Your own site · 80×15
<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>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,765 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. ✓ AI security review Fable 5.1 · 6 Sept 2026 📄 Read the review Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00085 $0.01765
Opus 5 $0.00043 $0.00882
Sonnet 5 $0.00017 $0.00353
Haiku 4.5 $0.00009 $0.00177

Measured 11d ago against content hash b754fab884b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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 11d 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.

src/qwenpaw/agents/tools/deprecated_browser/skills/browser_cdp-zh/SKILL.md · 201 lines

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:

  1. 扫描本地 CDP 端口
  2. 连接已有 Chrome(connect_cdp
  3. 显式指定 cdp_port 启动浏览器
  4. 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 opensnapshotclicktype 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:

Read the full file on GitHub · 201 lines

Changes

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.

  1. 11d ago First seen · 201 lines · 85 tokens per session scan A b754fab884b2

Subscribe to this mod's changes

browser_cdp is a skill published in the GitHub repository agentscope-ai/QwenPaw (34,741 stars, last pushed today), licensed Apache-2.0. It adds 85 tokens to every session and 1,765 once invoked, about $0.0004 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.

Related

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.

clacky-ai/openclacky · 83 tokens

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…

clacky-ai/openclacky · 175 tokens

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…

agentscope-ai/skills · 84 tokens

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.

agentscope-ai/skills · 97 tokens

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.

agentscope-ai/skills · 96 tokens

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.

agentscope-ai/skills · 64 tokens