← 返回 Skills 市场
projectamazonph

Agent Browser (projectamazonph)

作者 projectamazonph · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
12
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install projectamazonph-agent-browser
功能描述
Automate complex web workflows with fast, deterministic browser control using accessibility tree snapshots and session isolation.
使用说明 (SKILL.md)

Agent Browser Skill

Fast browser automation using accessibility tree snapshots with refs for deterministic element selection.

Why Use This Over Built-in Browser Tool

Use agent-browser when:

  • Automating multi-step workflows
  • Need deterministic element selection
  • Performance is critical
  • Working with complex SPAs
  • Need session isolation

Use built-in browser tool when:

  • Need screenshots/PDFs for analysis
  • Visual inspection required
  • Browser extension integration needed

Core Workflow

# 1. Navigate and snapshot
agent-browser open https://example.com
agent-browser snapshot -i --json

# 2. Parse refs from JSON, then interact
agent-browser click @e2
agent-browser fill @e3 "text"

# 3. Re-snapshot after page changes
agent-browser snapshot -i --json

Key Commands

Navigation

agent-browser open \x3Curl>
agent-browser back | forward | reload | close

Snapshot (Always use -i --json)

agent-browser snapshot -i --json                    # Interactive elements, JSON output
agent-browser snapshot -i -c -d 5 --json            # + compact, depth limit
agent-browser snapshot -s "#main" -i                # Scope to selector

Interactions (Ref-based)

agent-browser click @e2
agent-browser fill @e3 "text"
agent-browser type @e3 "text"
agent-browser hover @e4
agent-browser check @e5 | uncheck @e5
agent-browser select @e6 "value"
agent-browser press "Enter"
agent-browser scroll down 500
agent-browser drag @e7 @e8

Get Information

agent-browser get text @e1 --json
agent-browser get html @e2 --json
agent-browser get value @e3 --json
agent-browser get attr @e4 "href" --json
agent-browser get title --json
agent-browser get url --json
agent-browser get count ".item" --json

Check State

agent-browser is visible @e2 --json
agent-browser is enabled @e3 --json
agent-browser is checked @e4 --json

Wait

agent-browser wait @e2                     # Wait for element
agent-browser wait 1000                    # Wait ms
agent-browser wait --text "Welcome"        # Wait for text
agent-browser wait --url "**/dashboard"    # Wait for URL
agent-browser wait --load networkidle      # Wait for network
agent-browser wait --fn "window.ready === true"

Sessions (Isolated Browsers)

agent-browser --session admin open site.com
agent-browser --session user open site.com
agent-browser session list

State Persistence

agent-browser state save auth.json    # Save cookies/storage
agent-browser state load auth.json    # Load (skip login)

Screenshots & PDFs

agent-browser screenshot page.png
agent-browser screenshot --full page.png
agent-browser pdf page.pdf

Network Control

agent-browser network route "**/ads/*" --abort          # Block
agent-browser network route "**/api/*" --body '{"x":1}' # Mock
agent-browser network requests --filter api             # View

Cookies & Storage

agent-browser cookies                        # Get all
agent-browser cookies set name value
agent-browser storage local key              # Get localStorage
agent-browser storage local set key val

Tabs & Frames

agent-browser tab new https://example.com
agent-browser tab 2                          # Switch to tab
agent-browser frame @e5                      # Switch to iframe
agent-browser frame main                     # Back to main

Snapshot Output Format

{
  "success": true,
  "data": {
    "snapshot": "...",
    "refs": {
      "e1": {"role": "heading", "name": "Example Domain"},
      "e2": {"role": "button", "name": "Submit"},
      "e3": {"role": "textbox", "name": "Email"}
    }
  }
}

Best Practices

  • Always use -i flag — Focus on interactive elements
  • Always use --json — Easier to parse
  • Wait for stability — agent-browser wait --load networkidle
  • Save auth state — Skip login flows with state save/load
  • Use sessions — Isolate different browser contexts
  • Use --headed for debugging — See what's happening

Configuration

On this machine:

  • CLI: agent-browser (installed globally via npm, Node 24)
  • Chromium: /root/.cache/ms-playwright/chromium-1223/chrome-linux/chrome
  • Config: browser.executablePath set in ~/.openclaw/openclaw.json

Credits

Skill created by Yossi Elkrief (@MaTriXy) agent-browser CLI by Vercel Labs

安全使用建议
Install only if you understand that this bundle is not just an Agent Browser guide. Review or remove the self-improvement hook files before use, avoid global hook activation unless you explicitly want it across all projects, prefer project-local scoped matchers, and keep any saved browser auth-state files private and out of source control.
能力评估
Purpose & Capability
The main SKILL.md describes agent-browser automation, but the bundle contains self-improvement README content, learning assets, hook setup guides, shell scripts, and OpenClaw hook handlers that do not fit the advertised browser-automation purpose.
Instruction Scope
Browser commands are scoped to normal browser automation, but the bundled self-improvement instructions include prompt-time and bootstrap hook injection, learning capture, and promotion into agent guidance files, which are broader than the stated purpose.
Install Mechanism
The artifact documents project-level and user-level hook setup, including global configuration paths and OpenClaw hook enablement; these are opt-in, but persistent and under-disclosed by the browser skill title and summary.
Credentials
Browser state, cookies, storage, and sessions are proportionate for browser automation, but unrelated hook execution and reading command-output environment data are not proportionate to the advertised Agent Browser capability.
Persistence & Privilege
The skill documents saving browser auth state and includes persistent hook mechanisms; the hook content is mostly reminder-only and not destructive, but the combination has credential and cross-session persistence risk.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install projectamazonph-agent-browser
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /projectamazonph-agent-browser 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial publish — fast browser automation via accessibility tree snapshots with ref-based element selection
元数据
Slug projectamazonph-agent-browser
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Agent Browser (projectamazonph) 是什么?

Automate complex web workflows with fast, deterministic browser control using accessibility tree snapshots and session isolation. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 12 次。

如何安装 Agent Browser (projectamazonph)?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install projectamazonph-agent-browser」即可一键安装,无需额外配置。

Agent Browser (projectamazonph) 是免费的吗?

是的,Agent Browser (projectamazonph) 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Agent Browser (projectamazonph) 支持哪些平台?

Agent Browser (projectamazonph) 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Agent Browser (projectamazonph)?

由 projectamazonph(@projectamazonph)开发并维护,当前版本 v1.0.0。

💬 留言讨论