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 davidtoby/agent-skills --skill openclaw-browser-autogit clone --depth 1 https://github.com/davidtoby/agent-skillsWrote 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/davidtoby/agent-skills/openclaw-browser-auto)<a href="https://agentmods.dev/skills/davidtoby/agent-skills/openclaw-browser-auto"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/openclaw-browser-auto.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.00545 |
| Opus 5 | $0.00000 | $0.00272 |
| Sonnet 5 | $0.00000 | $0.00109 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
openclaw-browser-auto scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://127.0.0.1:9222/json/version What it actually says
OpenClaw 浏览器自动化配置
配置OpenClaw连接远程Chrome/CDP浏览器进行自动化操作。
适用场景
- 连接远程服务器的Chrome浏览器
- 使用Docker容器运行的无头浏览器
- 连接browserless.io云服务
配置步骤
1. 启动CDP浏览器容器
推荐使用 chromedp/headless-shell（轻量且保持会话）：
docker run -d --name browser-auto -p 9222:9222 --shm-size=512m chromedp/headless-shell:latest
验证CDP可用：
curl http://127.0.0.1:9222/json/version
2. 配置OpenClaw
在 ~/.openclaw/openclaw.json 中添加browser配置：
{
"browser": {
"enabled": true,
"defaultProfile": "remote-chrome",
"attachOnly": true,
"profiles": {
"remote-chrome": {
"cdpUrl": "http://127.0.0.1:9222",
"color": "#00AA00"
}
}
}
}
3. 重启Gateway
systemctl --user restart openclaw-gateway
4. 验证
openclaw browser status
关键配置项
| 配置项 | 说明 |
|---|---|
browser.enabled |
启用浏览器 |
browser.defaultProfile |
默认使用的浏览器配置名 |
browser.attachOnly |
true=不尝试启动本地浏览器，只连接远程 |
profiles.<name>.cdpUrl |
远程CDP地址 |
云服务方案
Browserless.io（付费）
{
"browser": {
"defaultProfile": "browserless",
"profiles": {
"browserless": {
"cdpUrl": "https://production-sfo.browserless.io?token=<API_KEY>"
}
}
}
}
常见问题
- 端口被占用 - 设置
attachOnly: true - 标签页丢失 - 使用 chromedp/headless-shell 而非 browserless/chrome
- 环境变量不生效 - 需要修改systemd服务配置
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 88 lines · 0 tokens per session scan A b8e5e3f248a6
openclaw-browser-auto is a skill published in the GitHub repository davidtoby/agent-skills (10 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 545 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
web-skills-protocol
Auto-discover and use Web Skills Protocol (WSP) skills when interacting with websites. Use this skill whenever the user asks you to interact with, use, or perform actions on a website or web service — such as searching a site, placing an order, deploying an app, or calling a web API. Before scraping HTML or guessing…
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Agent Browser
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
autofillin
Automated web form filling and file uploading skill with Playwright browser automation. Handles login persistence, form detection, file uploads, and waits for manual confirmation before submission.
browser-extension-builder
Expert in building browser extensions that solve real problems - Chrome, Firefox, and cross-browser extensions. Covers extension architecture, manifest v3, content scripts, popup UIs, monetization strategies, and Chrome Web Store publishing. Use when: browser extension, chrome extension, firefox addon, extension…