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 aAAaqwq/AGI-Super-Team --skill browser-profile-guidegit clone --depth 1 https://github.com/aAAaqwq/AGI-Super-TeamWrote 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/aaaaqwq/agi-super-team/browser-profile-guide)<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/browser-profile-guide"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/browser-profile-guide/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/aaaaqwq/agi-super-team/browser-profile-guide"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/browser-profile-guide.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 | $0.00025 | $0.01116 |
| Opus 5 | $0.00013 | $0.00558 |
| Sonnet 5 | $0.00005 | $0.00223 |
| Haiku 4.5 | $0.00003 | $0.00112 |
Grade A, and why
browser-profile-guide 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 4d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenClaw Browser Profile 完整指南
三种 Profile 用途速查
| Profile | 驱动 | 登录态 | 何时用 | 是否需要手动开浏览器 |
|---|---|---|---|---|
openclaw(默认) |
Playwright + Chrome CDP | ❌ 全新干净浏览器 | 自动化、批量操作、不需要登录 | ❌ 自动启动 |
user |
Playwright + Chrome CDP | ✅ 复用你已有的 Chrome 登录态 | 需要 GitHub/邮箱等已登录网站 | ✅ 需先手动开 Chrome |
sandbox |
Docker 内 Playwright | ❌ 隔离容器内全新浏览器 | 安全敏感操作 | ❌ 自动启动 |
你的当前配置(~/.openclaw/openclaw.json)
"browser": {
"headless": false,
"noSandbox": true,
"profiles": {
"user": {
"attachOnly": true, // 只连接已开的浏览器,不自动启动
"cdpPort": 9222, // Chrome 远程调试端口
"driver": "openclaw",
"color": "#00AA00"
}
}
}
注意:openclaw profile 没有显式定义,但是默认 profile,OpenClaw 会自动创建。
默认 Profile:openclaw(最常用)
browser(action="open", profile="openclaw", url="https://github.com")
browser(action="snapshot", profile="openclaw")
browser(action="act", profile="openclaw", ref="e1", kind="click")
- OpenClaw 自动管理浏览器生命周期
- 每次启动是干净的浏览器环境
- CDP 端口:18800(
openclaw profile)
user Profile — 复用已有登录态
前置条件:你必须先手动打开 Chrome 并启用远程调试
# macOS
/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome \
--remote-debugging-port=9222 \
--user-data-dir="$HOME/Library/Application Support/Google/Chrome"
# Linux
google-chrome --remote-debugging-port=9222
你的配置里 user profile 已设为 attachOnly: true,意味着:
- 如果 Chrome 没开 → 不会自动启动 → 会报错
- Chrome 开着且端口 9222 在监听 → 自动连接
// 需要登录 GitHub?用 user profile
browser(action="open", profile="user", url="https://github.com")
browser(action="snapshot", profile="user")
统一规则(你们团队所有人遵守)
任务需要登录网站(GitHub/邮箱/社交媒体)
→ profile="user" + 先手动开 Chrome --remote-debugging-port=9222
普通自动化、批量操作、无需登录
→ profile="openclaw"(默认,可省略 profile 参数)
CDP 直连模式(更快)
当前配置已有 chromeCdp 模式(browser.chromeCdp: true),这让 OpenClaw 直接用 Chrome DevTools Protocol,绕过 Playwright 的额外开销。
常用操作示例
// 1. 普通自动化(用默认 openclaw profile)
browser(action="open", url="https://example.com")
browser(action="snapshot")
// 2. 需要登录的网站
browser(action="open", profile="user", url="https://github.com/settings/applications")
browser(action="snapshot")
// 3. 截图
browser(action="screenshot", fullPage=true)
// 4. 复杂交互(先用 snapshot 获取 refs)
browser(action="snapshot")
// → 拿到 @e1, @e2 等 refs
browser(action="act", ref="e1", kind="click")
browser(action="act", ref="e3", kind="type", text="hello world")
// 5. PDF 导出
browser(action="pdf")
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.
- 4d ago First seen · 118 lines · 25 tokens per session scan A 04ef6316486e
browser-profile-guide is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (91 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 1,116 once invoked, about $0.0001 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 2026-09-05.
Other skills, from other repositories
browser-check
Drive a real browser and come back with a MEASUREMENT rather than an impression - console errors and >=400 responses as counts, computed styles as JSON when appearance is disputed. Use when work touches UI, when a review must verify one, or when fidelity-gate asks for its measurement.
qa
QA testing skill with real browser automation. Use when asked to "test this site", "QA this page", "check for visual bugs", "verify the deploy", or when Hydra needs browser validation for UI changes. Requires the browse binary.
chrome-devtools
Drive the machine Chrome debug browser via OpenClaw-managed MCP (chrome-devtools). Use for page navigation, snapshots, screenshots, clicks, forms, console/network inspection — not for host shell risk.
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.
browser
Browser automation via the agent-browser CLI. Use when the user needs to drive websites or Electron desktop apps — navigating, filling forms, clicking, screenshots, extracting data, testing web apps, visual UI checks, the Pi Dashboard's Electron shell, or the user's own logged-in browser (SSO/2FA sites). Triggers…
prompt-tuning
Tune a prompt, or anything whose quality is measured by non-deterministic model output, without chasing noise - a noise baseline before the first edit, medians over repeated runs, enforcement AFTER generation rather than in the wording. Use when iterating on prompts or model-judged output.