← 返回 Skills 市场

Agent Browser Clawdbot Local

Name: Agent Browser Clawdbot Local
Author: reknottycat

作者 reknottycat · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

总下载

当前安装

版本数

在 OpenClaw 中安装

/install agent-browser-clawdbot-local

功能描述

Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection

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
# Or via env: AGENT_BROWSER_SESSION=admin agent-browser ...

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

Example: Search and Extract

agent-browser open https://www.google.com
agent-browser snapshot -i --json
# AI identifies search box @e1
agent-browser fill @e1 "AI agents"
agent-browser press Enter
agent-browser wait --load networkidle
agent-browser snapshot -i --json
# AI identifies result refs
agent-browser get text @e3 --json
agent-browser get attr @e4 "href" --json

Example: Multi-Session Testing

# Admin session
agent-browser --session admin open app.com
agent-browser --session admin state load admin-auth.json
agent-browser --session admin snapshot -i --json

# User session (simultaneous)
agent-browser --session user open app.com
agent-browser --session user state load user-auth.json
agent-browser --session user snapshot -i --json

Installation

npm install -g agent-browser
agent-browser install                     # Download Chromium
agent-browser install --with-deps         # Linux: + system deps

Credits

Skill created by Yossi Elkrief (@MaTriXy)

agent-browser CLI by Vercel Labs

安全使用建议

This skill appears to be a legitimate CLI-driven browser automation tool, but take these precautions before installing: - Verify the upstream package and repo: check the GitHub repo (https://github.com/vercel-labs/agent-browser) and the npm package owner/release history to ensure authenticity. - Expect the CLI to download Chromium and write state files (cookies/localStorage). Treat saved state files as sensitive — they can contain session tokens. - Run installs in a sandbox or isolated VM if possible; avoid installing globally on a critical host until verified. - Review the npm package contents (and any download URLs) for unexpected code or network endpoints and prefer pinned checksums. - Note the registry metadata mismatches (declared required binaries/env vars vs. SKILL.md embedded metadata, and differing _meta.json owner/slug); ask the publisher to clarify these inconsistencies before trusting the skill. - If you will use the skill with accounts, rotate credentials or use test accounts to limit exposure.

能力评估

ℹ Purpose & Capability

SKILL.md behavior (agent-browser CLI commands for snapshots, ref-based interaction, sessions, state save/load, network control) is coherent with the stated purpose (headless browser automation). However the registry metadata claims no required binaries/env vars while SKILL.md and its embedded metadata declare a required 'agent-browser' command and show use of npm for installation — a mismatch in declared requirements.

⚠ Instruction Scope

Instructions ask the agent to run many commands that will capture page content (snapshots JSON), save/load auth state (cookies/storage), and inspect or mock network requests. These are expected for a browser automation tool but give the agent access to potentially sensitive site content and account sessions. The SKILL.md does not instruct exfiltration, but it enables collection and local storage of credentials/session data and network traffic viewing.

⚠ Install Mechanism

Although the registry has no install spec, SKILL.md instructs using 'npm install -g agent-browser' and a subsequent 'agent-browser install' that downloads Chromium. npm packages and binary downloads introduce moderate-to-high risk if the package or its upstream downloads are unverified or malicious — the skill provides no pinned source URL or checksum.

ℹ Credentials

The skill does not require environment variables in registry metadata, but SKILL.md references an optional AGENT_BROWSER_SESSION and uses state save/load files (e.g., admin-auth.json) which can contain cookies/session tokens. No unrelated credentials are requested, but file-based session persistence can expose sensitive auth data if misused.

✓ Persistence & Privilege

The skill is not always-enabled and does not request special platform privileges. It does instruct creating/loading local state files and downloading Chromium, which affects only the local environment and not other skills or system-wide settings.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install agent-browser-clawdbot-local
安装完成后，直接呼叫该 Skill 的名称或使用 /agent-browser-clawdbot-local 触发
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 release of agent-browser skill for headless browser automation - Provides CLI optimized for AI agents using accessibility tree snapshots and ref-based deterministic element selection - Supports advanced workflows: navigation, interaction, state checks, multi-session isolation, and network control - Includes commands for information extraction, state persistence, screenshots, PDFs, cookies, storage, tabs, and frames - Detailed documentation with practical examples and best practices

元数据

Slug agent-browser-clawdbot-local

版本 1.0.0

许可证 MIT-0

累计安装 3

当前安装数 1

历史版本数 1

常见问题