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 hyqibot/token-free-openclaw --skill browser_cdpgit clone --depth 1 https://github.com/hyqibot/token-free-openclawWrote 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/hyqibot/token-free-openclaw/browser_cdp)<a href="https://agentmods.dev/skills/hyqibot/token-free-openclaw/browser_cdp"><img src="https://agentmods.dev/badge/skills/hyqibot/token-free-openclaw/browser_cdp/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/hyqibot/token-free-openclaw/browser_cdp"><img src="https://agentmods.dev/badge/skills/hyqibot/token-free-openclaw/browser_cdp.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 | $0.00128 | $0.01911 |
| Opus 5 | $0.00064 | $0.00955 |
| Sonnet 5 | $0.00026 | $0.00382 |
| Haiku 4.5 | $0.00013 | $0.00191 |
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 10d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
浏览器 CDP 连接参考
Chrome DevTools Protocol(CDP) 允许外部程序连接并控制一个已在运行的 Chrome 进程。本 skill 覆盖三类场景:
- 扫描本地 CDP 端口 — 发现正在运行的可连接 Chrome
- 连接已有 Chrome — 附加到外部 Chrome,不影响其运行
- 启动暴露 CDP 端口的浏览器 — 让 Playwright 启动的浏览器对外可见
⚠️ 隐私提示:使用 CDP 前请知晓
- 默认模式(
start不带cdp_port):浏览器完全由 Playwright 私有管理,历史记录、Cookies、登录态不会暴露给任何外部程序。- CDP 模式(
start+cdp_port或connect_cdp):任何能访问该端口的程序都可以读取浏览器的完整历史记录、Cookies、当前页面内容、已保存密码等敏感信息。仅在信任的本地环境中使用,不要在公共网络或多用户服务器上暴露 CDP 端口。
⚠️ 单实例限制:一个 workspace 同时只能运行/连接一个浏览器
无论是 Playwright 启动的浏览器还是 CDP 连接,同一 workspace 内同一时间只允许存在一个。需要切换时,必须先执行
stop,再启动或连接新的浏览器。
何时使用
仅在用户明确表达以下意图时才使用本 skill:
- 用户说:「连接到我已打开的 Chrome」「扫描一下本地有没有可连接的浏览器」
- 用户明确希望多个 agent 或外部工具共享同一个浏览器实例
- 用户明确要求浏览器对外可见/可调试
- 用户主动提到 CDP、远程调试端口等概念
以下情况不要使用 CDP 模式,直接用普通 start 即可:
- 用户只是说「打开浏览器」「帮我打开某网站」,没有提到共享或调试
- 用户没有明确说明需要暴露浏览器给其他程序
- 不确定用户是否了解 CDP 的隐私风险
使用前须告知用户 CDP 模式会暴露浏览器历史、Cookies 等敏感信息,确认用户知情后再操作。
场景一:扫描本地 CDP 端口
默认扫描端口范围 9000–10000,并发探测,速度很快。
{"action": "list_cdp_targets"}
指定单个端口:
{"action": "list_cdp_targets", "port": 9222}
自定义扫描范围(未找到时可扩大范围):
{"action": "list_cdp_targets", "port_min": 8000, "port_max": 12000}
成功返回示例:
{
"ok": true,
"found": {
"9222": [{"title": "New Tab", "url": "chrome://newtab/", ...}]
},
"message": "Found CDP endpoints on port(s): 9222"
}
未找到时 返回 ok: false,并提示扩大范围或确认 Chrome 是否以 --remote-debugging-port=N 启动。
场景二:连接已有 Chrome(connect_cdp)
先扫描到端口后,再连接:
{"action": "connect_cdp", "cdp_url": "http://localhost:9222"}
- 连接成功后可正常使用
open、snapshot、click、type等所有操作 - 不会影响 Chrome 进程:执行
stop时只断开 Playwright 连接,Chrome 继续运行 - 连接期间每次操作前会自动检查连接是否正常,断开时返回错误提示重新连接
- 隐私风险:连接后 agent 可读取该 Chrome 的完整 Cookies、历史记录、当前页面内容,请确认用户知情
- 单实例:如果当前已有浏览器在运行(无论是 Playwright 启动的还是另一个 CDP 连接),必须先
stop再连接
场景三:启动带 CDP 端口的浏览器
让 Playwright 启动浏览器时暴露指定 CDP 端口,其他工具可同时连接:
{"action": "start", "cdp_port": 9222}
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.
- 10d ago First seen · 182 lines · 128 tokens per session scan A a181a995b3cd
browser_cdp is a skill published in the GitHub repository hyqibot/token-free-openclaw (122 stars, last pushed 18d ago), licensed Apache-2.0. It adds 128 tokens to every session and 1,911 once invoked, about $0.0006 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
add-tavily-tool
Add Tavily Search and Extract as keyless remote MCP tools for selected NanoClaw agent groups. Use when installing Tavily web search or URL extraction without an API key.
agent-browser
Browse the web for any task — research topics, read articles, interact with web apps, fill forms, take screenshots, extract data, and test web pages. Use whenever a browser would be useful, not just when the user explicitly asks.
browser-cdp
Use this skill when you need to control a Chrome browser via CDP (Chrome DevTools Protocol) to reuse existing login sessions. Covers: launching Chrome in debug mode, opening URLs, waiting for page load, evaluating JavaScript, taking snapshots, and extracting auth tokens. Trigger phrases: browser automation, CDP…
browser-automation
Playwright-based browser automation patterns for autonomous web interaction.
dingtalk_channel_connect
A browser-based setup guide for connecting a MateClaw assistant to DingTalk, a Chinese workplace messaging platform. It creates and configures a DingTalk application, then publishes the configuration.
browser_cdp
A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.