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 L-LesterYu/OpenClaw-hot-skills-zh --skill agent-browser-zhgit clone --depth 1 https://github.com/L-LesterYu/OpenClaw-hot-skills-zhWrote 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/l-lesteryu/openclaw-hot-skills-zh/agent-browser-zh)<a href="https://agentmods.dev/skills/l-lesteryu/openclaw-hot-skills-zh/agent-browser-zh"><img src="https://agentmods.dev/badge/skills/l-lesteryu/openclaw-hot-skills-zh/agent-browser-zh/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/l-lesteryu/openclaw-hot-skills-zh/agent-browser-zh"><img src="https://agentmods.dev/badge/skills/l-lesteryu/openclaw-hot-skills-zh/agent-browser-zh.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00101 | $0.02264 |
| Opus 5 | $0.00051 | $0.01132 |
| Sonnet 5 | $0.00020 | $0.00453 |
| Haiku 4.5 | $0.00010 | $0.00226 |
Grade A, and why
agent-browser-zh 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 13d 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-browser 技能
真正为 AI 智能体打造的浏览器自动化工具。由 Vercel Labs 专门为 LLM 驱动的工作流构建。
为什么这比替代方案更好
1. 确定性引用（游戏规则改变者）
传统工具的问题：
- CSS 选择器在网站更改时会失效
- XPath 脆弱且难以阅读
- 基于坐标的点击在响应式布局上失败
- 基于视觉的方法速度慢且成本高
agent-browser 的解决方案：
# 1. 获取带有稳定引用的快照
agent-browser snapshot -i --json
# 输出: - button "Submit" [ref=e2]
# 2. 永久使用该引用 — 它指向确切的元素
agent-browser click @e2
- 引用是确定性的 —
@e2始终指向快照中的同一元素 - 无需重新查询 DOM — 直接引用更快、更可靠
- 针对 AI 优化 — LLM 自然地解析无障碍树，而不是 CSS 混合体
2. 无障碍树 > 截图/HTML
传统工具提供原始 HTML（嘈杂）或截图（需要视觉模型）。
agent-browser 提供无障碍树 — 人类（或屏幕阅读器）感知的干净、语义化表示：
- heading "Billing" [level=1]
- link "Make a payment" [ref=e10]
- button "Submit" [ref=e2]
- textbox "Email" [ref=e3]
- 语义角色（button、link、textbox、heading）
- 人类可读的标签
- 层次结构
- 完美适配 LLM 理解
3. 为 AI 智能体构建
| 功能 | 传统工具 | agent-browser |
|---|---|---|
| 元素定位 | 脆弱的选择器 | 确定性引用 |
| 页面理解 | 原始 HTML | 无障碍树 |
| 输出格式 | 文本日志 | 结构化 JSON |
| 速度 | 慢（每个命令启动完整浏览器） | 快（守护进程持久化） |
| AI 集成 | 事后补充 | 专用构建 |
4. 快速架构
- Rust CLI — 原生二进制文件，即时命令解析
- Node.js 守护进程 — 浏览器在命令之间保持活跃
- 首次命令： ~2秒（守护进程启动）
- 后续命令： ~100毫秒
前置条件
npm install -g agent-browser
agent-browser install # 下载 Chromium（约30秒）
核心 AI 工作流
为 LLM 智能体设计的工作流：
# 步骤 1：导航
agent-browser open https://example.com
# 步骤 2：获取结构化快照（AI "看到" 页面）
agent-browser snapshot -i --json
# 步骤 3：AI 从 JSON 中选择引用，执行操作
agent-browser click @e2
agent-browser fill @e3 "[email protected]"
# 步骤 4：更改后重新快照（状态验证）
agent-browser snapshot -i --json
# 步骤 5：完成
agent-browser close
命令
导航
agent-browser open example.com
agent-browser open example.com --json # JSON 响应
agent-browser open example.com --headed # 可见浏览器
快照（杀手级功能）
agent-browser snapshot # 完整无障碍树
agent-browser snapshot -i # 仅交互元素（更快）
agent-browser snapshot -i --json # 用于 AI 解析的 JSON
agent-browser snapshot -i -c -d 5 --json # 紧凑，深度限制
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.
- 13d ago First seen · 254 lines · 101 tokens per session scan A 990343bbecf2
agent-browser-zh is a skill published in the GitHub repository L-LesterYu/OpenClaw-hot-skills-zh (54 stars, last pushed 5mo ago), licensed MIT. It adds 101 tokens to every session and 2,264 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…