browser-use

browser-use is a skill for Claude Code from aAAaqwq/AGI-Super-Team. It costs 57 tokens per session (2,252 once invoked), scanned A, original, MIT.

An AI-driven browser automation tool that reads web pages, chooses actions, and carries out tasks from a natural-language description. Unlike a fixed script, it can make decisions while interacting with changing pages.

In plain words
What is it for?
Use it to navigate dynamic sites, complete multi-step browser tasks, and automate interactions where the next action depends on what the page shows.
Why use it?
It reduces the need to write and maintain exact element selectors for complex websites. Its required browser cleanup also helps prevent leftover Chrome processes from consuming resources.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

Part of the agi-super-team plugin — 193 skills, 1 agent shipped together

Good fit Use it to navigate dynamic sites, complete multi-step browser tasks, and automate interactions where the next action depends on what the page shows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aaaaqwq/agi-super-team/browser-use
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 aAAaqwq/AGI-Super-Team --skill browser-use
Clone the repo
git clone --depth 1 https://github.com/aAAaqwq/AGI-Super-Team

Made for: Claude Code.

Or install agi-super-team, the plugin that ships this one along with the rest of its 193 skills, 1 agent.

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-use

README.md
[![agentmods](https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/browser-use.svg)](https://agentmods.dev/skills/aaaaqwq/agi-super-team/browser-use)
Your own site
<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/browser-use"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/browser-use.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,252 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Tool Misuse · line 121
    Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.
    Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
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 $0.00057 $0.02252
Opus 5 $0.00028 $0.01126
Sonnet 5 $0.00011 $0.00450
Haiku 4.5 $0.00006 $0.00225

Measured 3d ago against content hash c6f2e1e05672, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

browser-use 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 3d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

subprocess.run(['pkill', '-f', 'chrome'], capture_output=True)
skills/browser-use/SKILL.md · 365 lines

How it starts

The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.

browser-use 智能浏览器自动化

概述

browser-use 是一个 AI 驱动的浏览器自动化工具,它使用 LLM 来:

  • 理解网页内容
  • 智能决策下一步操作
  • 自动完成任务

与 Playwright 的区别:

特性 Playwright browser-use
控制方式 预编程脚本 AI智能决策
适应性 页面变化需重写 自动适应
Token消耗 较低但需调试 智能精简
复杂交互 需精确选择器 自然语言描述
维护成本

⚠️ 资源清理原则(强制)

所有涉及浏览器的 cron 任务完成后,必须自动关闭 Chrome 进程!

import asyncio
from browser_use import Agent

async def main():
    agent = Agent(task="...", llm=llm)
    result = await agent.run()

    # ⚠️ 任务结束后必须显式关闭浏览器
    if hasattr(agent, 'browser') and agent.browser:
        await agent.browser.close()

    # ⚠️ 推荐在脚本结束时强制清理残留进程
    import subprocess
    subprocess.run(['pkill', '-f', 'chrome'], capture_output=True)

    return result

原因: 避免内存泄漏和资源占用,防止 Gateway CPU 100% 过载

安装状态

✅ 已安装:

  • browser-use 0.11.11
  • browser-use-sdk 2.0.15

快速开始

基本用法

import asyncio
from browser_use import Agent
from langchain_openai import ChatOpenAI

async def main():
    agent = Agent(
        task="打开 polymarket.com,查看 Fed 利率市场",
        llm=ChatOpenAI(model="gpt-4o"),
    )
    result = await agent.run()
    print(result)

asyncio.run(main())

使用自定义 LLM(推荐配置)

⚠️ 重要:your-provider API 是 Anthropic 格式,不是 OpenAI 格式!必须使用 ChatAnthropic

from browser_use.llm.anthropic.chat import ChatAnthropic

# your-provider API(Anthropic 兼容)✅ 推荐
llm = ChatAnthropic(
    model="claude-sonnet-4-6",
    base_url="https://your-anthropic-proxy.example.com",  # 注意:不加 /v1
    api_key="your-api-key",  # 或从 pass show api/your-provider 获取
)

agent = Agent(
    task="你的任务",
    llm=llm,
)
# ❌ 错误用法:不要用 ChatOpenAI + your-provider
# from browser_use.llm.openai.chat import ChatOpenAI  # 这个不行!your-provider 不支持 OpenAI 格式
# 如果使用 OpenAI 兼容 API(如 Provider-B),用 ChatOpenAI:
from browser_use.llm.openai.chat import ChatOpenAI
llm = ChatOpenAI(
    model="gpt-4o",
    base_url="https://ai.9w7.cn/v1",
    api_key="your-api-key",
)

Read the full file on GitHub · 365 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. 3d ago First seen · 365 lines · 57 tokens per session scan A c6f2e1e05672

Subscribe to this mod's changes

browser-use is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (91 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 2,252 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.

Related

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.

jjanczur/tyran · 58 tokens

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.

blueberrycongee/termcanvas · 50 tokens

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.

yunsii/wezdeck · 44 tokens

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.

builderz-labs/mission-control · 34 tokens

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…

BlackBeltTechnology/pi-agent-dashboard · 92 tokens

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.

jjanczur/tyran · 58 tokens