browser

A browser-automation skill that controls a web browser to load pages, interact with forms and buttons, inspect page structure, and capture screenshots.

In plain words
What is it for?
Use it to check rendered interfaces, test end-to-end user flows, extract dynamic content, debug front-end errors, and save screenshots.
Why use it?
It lets an agent test what a user actually sees and handles pages whose content is created by JavaScript. It can also expose browser console errors and network requests.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/nullskymc/aurevoy/browser
Any agent
npx skills add nullskymc/Aurevoy --skill browser
Clone the repo
git clone --depth 1 https://github.com/nullskymc/Aurevoy

Made for: Claude Code, Codex.

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 838 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00063 $0.00838
Opus 5 $0.00032 $0.00419
Sonnet 5 $0.00013 $0.00168
Haiku 4.5 $0.00006 $0.00084

Measured 2d ago against content hash 332b3bb0508d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

browser 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 2d 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.

apps/agent/skills/builtin/browser/SKILL.md · 106 lines

What it actually says

Browser 浏览器自动化技能

你启用了浏览器自动化能力。通过 Playwright MCP Server,你可以操控无头浏览器来:

可用能力

页面导航与交互

  • 打开任意 URL 并等待页面加载完成
  • 点击按钮、填写表单、触发事件
  • 页面滚动、切换标签页
  • 等待特定元素出现或网络空闲

信息提取

  • 截图:捕获页面可视区域的 PNG 截图
  • DOM 摘要:获取页面结构的可访问性树(accessibility tree),比原始 HTML 更精简易读
  • 控制台输出:抓取浏览器控制台的错误和警告信息
  • 网络请求:监控页面发出的 API 请求和响应

测试与验证

  • 验证页面功能是否正常
  • 检查 UI 渲染效果
  • 排查前端错误
  • 端到端工作流测试

使用指南

何时使用浏览器

  • 需要查看页面实际渲染效果时
  • 需要抓取 JavaScript 动态渲染的内容(web_fetch 只能获取静态 HTML/文本)
  • 需要模拟用户操作(登录、搜索、提交表单)
  • 需要调试前端错误
  • 需要截图作为产物交付

何时不用浏览器

  • 仅获取静态页面正文 → 用 web_fetch(更快更轻量)
  • 仅搜索信息 → 用 web_search
  • 仅读取本地文件 → 用 read_file

操作原则

  1. 先轻后重:优先用 web_fetch 获取内容,确认需要 JS 渲染再用浏览器
  2. 快速收窄:打开页面后先看 DOM 摘要定位关键元素,再精确交互
  3. 保存证据:重要页面状态用截图保存为 artifact
  4. 处理错误:检查控制台输出中的错误信息
  5. 超时处理:页面加载慢时设置合理的超时时间

首次配置

浏览器能力通过 Playwright MCP Server 提供。需要先安装和配置:

# 安装 Playwright MCP Server
npm install -g @anthropic/mcp-server-playwright

# 在 Aurevoy 设置中配置 MCP Server:
# command: npx
# args: ["-y", "@anthropic/mcp-server-playwright"]

或者在 AUREVOY_MCP_SERVERS_JSON 环境变量中配置:

{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": ["-y", "@anthropic/mcp-server-playwright"],
      "enabled": true
    }
  }
}

配置后重启 Aurevoy,浏览器相关工具会自动注册。

输出格式

浏览器操作后请呈现:

## 浏览器操作结果

### 页面: <URL>
### 状态: <加载状态>

### DOM 摘要
<关键元素和结构>

### 截图
<截图已保存为 artifact>

### 控制台输出
<错误/警告信息>

### 分析
<基于以上信息的分析>
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. 2d ago First seen · 106 lines · 63 tokens per session scan A 332b3bb0508d

Subscribe to this mod's changes

browser is a skill published in the GitHub repository nullskymc/Aurevoy (10 stars, last pushed 26d ago), licensed MIT. It adds 63 tokens to every session and 838 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

dify

Use when building LLM applications with visual workflow — RAG knowledge bases, AI agents, chatbots with drag-and-drop orchestration. Dify: open-source LLM app platform supporting 30+ models (OpenAI, Claude, DeepSeek, Ollama, Qwen, GLM) with Docker deployment.

znlgis/opengis-skills · 66 tokens

ai-skills

Use when building LLM applications, RAG knowledge bases, AI agents, terminal coding agents, multi-model orchestration, plugin-based agent harnesses, or file translation. Index of 9 skills: Dify, Hermes Agent, OpenClaw, OpenCode, Pi, DocuTranslate, Oh-My-OpenAgent, Superpowers-zh, DeepSeek Harness.

znlgis/opengis-skills · 79 tokens

Web2Skill

Convert one public website URL or an explicit batch of public URLs into a reusable skill zip backed by rendered HTML snapshots and a bounded JSONL retrieval index. Use to discover a documentation directory from one URL, crawl a supplied URL set sequentially, generate a source profile, or package indexed web content as…

zhimaAi/chatwiki · 67 tokens

Book2Skill

Convert one or more TXT, Markdown, DOCX, or PDF documents into a reusable skill zip backed by normalized Markdown, extracted images, and a grounded JSONL knowledge index. Invoke this skill before inspecting task files, then execute its workflow directly without listing directories.

zhimaAi/chatwiki · 56 tokens

3d-web-experience

Expert in building 3D experiences for the web - Three.js, React Three Fiber, Spline, WebGL, and interactive 3D scenes. Covers product configurators, 3D portfolios, immersive websites, and bringing dep.

ranbot-ai/awesome-skills · 53 tokens

advogado-criminal

Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal.

ranbot-ai/awesome-skills · 42 tokens