MateClaw is a pluggable agent runtime that coordinates AI agents, tools, conversations, memory, and workflows. It is designed for personal and multi-user AI assistants, including agents used through chat platforms. Catalogue add-ons provide skills for extending its agent workflows.
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 mateaix/mateclaw --skill browser_cdpgit clone --depth 1 https://github.com/mateaix/mateclawWrote 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/mateaix/mateclaw/browser_cdp)<a href="https://agentmods.dev/skills/mateaix/mateclaw/browser_cdp"><img src="https://agentmods.dev/badge/skills/mateaix/mateclaw/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/mateaix/mateclaw/browser_cdp"><img src="https://agentmods.dev/badge/skills/mateaix/mateclaw/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 | $0.00044 | $0.00762 |
| Opus 5.5 | $0.00018 | $0.00305 |
| Sonnet 5.5 | $0.00009 | $0.00152 |
| Haiku 4.5 | $0.00004 | $0.00076 |
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.
What it actually says
浏览器 CDP 使用
仅在用户明确提出以下需求时使用本技能：
- 连接到已打开的 Chrome（附着现有实例）
- 扫描本机有哪些 CDP 端口可用
- 用固定调试端口启动浏览器
- 让多个工具 / Agent 共享同一浏览器
普通"打开浏览器"需求请用 browser_visible 技能。
场景一：扫描本机 CDP 端口
browser_use(action="list_cdp_targets")
扫描指定端口：
browser_use(action="list_cdp_targets", cdpPort=9222)
场景二：连接已有 Chrome
用户已手动用调试端口启动了 Chrome：
browser_use(action="connect_cdp", url="http://localhost:9222")
连接后可正常使用 open / snapshot / click / type 等操作。
注意：
stop只断开连接，不会关闭用户的 Chrome 进程。
场景三：启动时指定固定 CDP 端口
browser_use(action="start", cdpPort=9222)
可见窗口 + 固定端口：
browser_use(action="start", headed=true, cdpPort=9222)
仅在用户明确要求固定端口时才传
cdpPort，否则让系统自动选择空闲端口以避免冲突。
手动启动 Chrome（带调试端口）
若用户需要先手动打开 Chrome 再连接：
macOS：
execute_shell_command(
command="\"/Applications/Google Chrome.app/Contents/MacOS/Google Chrome\" --remote-debugging-port=9222 --no-first-run --no-default-browser-check"
)
Windows：
execute_shell_command(
command="\"C:\\Program Files\\Google\\Chrome\\Application\\chrome.exe\" --remote-debugging-port=9222 --no-first-run"
)
Linux：
execute_shell_command(
command="google-chrome --remote-debugging-port=9222 --no-first-run &"
)
stop 行为区别
| 启动方式 | stop 效果 |
|---|---|
browser_use(action="start") |
断开连接 + 关闭 Chrome 进程 |
browser_use(action="connect_cdp", ...) |
仅断开连接，不关闭外部 Chrome |
与 browser_visible 的分工
| 需求 | 用哪个技能 |
|---|---|
| 显示 / 隐藏浏览器窗口 | browser_visible |
| 连接 / 暴露 / 扫描 CDP 端口 | browser_cdp（本技能） |
安全提醒
- CDP 端口暴露后，本机任何进程都可以控制该浏览器（包括读取 Cookies）
- 不要在公共 / 多用户服务器上暴露 CDP 端口
- 用完后及时
stop断开连接
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 · 101 lines · 44 tokens per session scan A 9af168daa864
browser_cdp is a skill published in the GitHub repository mateaix/mateclaw (1,164 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 762 once invoked, about $0.0002 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-doctor
Read-only health check on browser-control setup. Verifies browser binary, Playwright MCP Bridge extension presence, token file mode/contents, AIWG MCP registration, provider config injection, and optional workspace allow-list. Outputs pass/fail per check with remediation commands.
pentest-client-advanced
Advanced client-side attacks — CORS misconfiguration, WebSocket security, clickjacking, postMessage abuse, CSS injection, and browser storage vulnerabilities.
pentest-ctf-binary
Binary exploitation (Pwn) and reverse engineering tools for CTF challenges and software analysis.
pentest-ctf-forensics
Digital forensics, steganography, and packet analysis for CTF challenges and investigation.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).