功能描述

A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured co...

使用说明 (SKILL.md)

Browser Automation with agent-browser

Name: Claw Browser Automation
Author: zhangsaizz

Installation

npm recommended

npm install -g agent-browser
agent-browser install
agent-browser install --with-deps

From Source

git clone https://github.com/vercel-labs/agent-browser
cd agent-browser
pnpm install
pnpm build
agent-browser install

Quick start

agent-browser open \x3Curl>        # Navigate to page
agent-browser snapshot -i       # Get interactive elements with refs
agent-browser click @e1         # Click element by ref
agent-browser fill @e2 "text"   # Fill input by ref
agent-browser close             # Close browser

Core workflow

Navigate: agent-browser open \x3Curl>
Snapshot: agent-browser snapshot -i (returns elements with refs like @e1, @e2)
Interact using refs from the snapshot
Re-snapshot after navigation or significant DOM changes

Commands

Navigation

agent-browser open \x3Curl>      # Navigate to URL
agent-browser back            # Go back
agent-browser forward         # Go forward
agent-browser reload          # Reload page
agent-browser close           # Close browser

Snapshot (page analysis)

agent-browser snapshot            # Full accessibility tree
agent-browser snapshot -i         # Interactive elements only (recommended)
agent-browser snapshot -c         # Compact output
agent-browser snapshot -d 3       # Limit depth to 3
agent-browser snapshot -s "#main" # Scope to CSS selector

Interactions (use @refs from snapshot)

agent-browser click @e1           # Click
agent-browser dblclick @e1        # Double-click
agent-browser focus @e1           # Focus element
agent-browser fill @e2 "text"     # Clear and type
agent-browser type @e2 "text"     # Type without clearing
agent-browser press Enter         # Press key
agent-browser press Control+a     # Key combination
agent-browser keydown Shift       # Hold key down
agent-browser keyup Shift         # Release key
agent-browser hover @e1           # Hover
agent-browser check @e1           # Check checkbox
agent-browser uncheck @e1         # Uncheck checkbox
agent-browser select @e1 "value"  # Select dropdown
agent-browser scroll down 500     # Scroll page
agent-browser scrollintoview @e1  # Scroll element into view
agent-browser drag @e1 @e2        # Drag and drop
agent-browser upload @e1 file.pdf # Upload files

Get information

agent-browser get text @e1        # Get element text
agent-browser get html @e1        # Get innerHTML
agent-browser get value @e1       # Get input value
agent-browser get attr @e1 href   # Get attribute
agent-browser get title           # Get page title
agent-browser get url             # Get current URL
agent-browser get count ".item"   # Count matching elements
agent-browser get box @e1         # Get bounding box

Check state

agent-browser is visible @e1      # Check if visible
agent-browser is enabled @e1      # Check if enabled
agent-browser is checked @e1      # Check if checked

Screenshots & PDF

agent-browser screenshot          # Screenshot to stdout
agent-browser screenshot path.png # Save to file
agent-browser screenshot --full   # Full page
agent-browser pdf output.pdf      # Save as PDF

Video recording

agent-browser record start ./demo.webm    # Start recording (uses current URL + state)
agent-browser click @e1                   # Perform actions
agent-browser record stop                 # Stop and save video
agent-browser record restart ./take2.webm # Stop current + start new recording

Recording creates a fresh context but preserves cookies/storage from your session. If no URL is provided, it automatically returns to your current page. For smooth demos, explore first, then start recording.

Wait

agent-browser wait @e1                     # Wait for element
agent-browser wait 2000                    # Wait milliseconds
agent-browser wait --text "Success"        # Wait for text
agent-browser wait --url "/dashboard"    # Wait for URL pattern
agent-browser wait --load networkidle      # Wait for network idle
agent-browser wait --fn "window.ready"     # Wait for JS condition

Mouse control

agent-browser mouse move 100 200      # Move mouse
agent-browser mouse down left         # Press button
agent-browser mouse up left           # Release button
agent-browser mouse wheel 100         # Scroll wheel

Semantic locators (alternative to refs)

agent-browser find role button click --name "Submit"
agent-browser find text "Sign In" click
agent-browser find label "Email" fill "[email protected]"
agent-browser find first ".item" click
agent-browser find nth 2 "a" text

Browser settings

agent-browser set viewport 1920 1080      # Set viewport size
agent-browser set device "iPhone 14"      # Emulate device
agent-browser set geo 37.7749 -122.4194   # Set geolocation
agent-browser set offline on              # Toggle offline mode
agent-browser set headers '{"X-Key":"v"}' # Extra HTTP headers
agent-browser set credentials user pass   # HTTP basic auth
agent-browser set media dark              # Emulate color scheme

Cookies & Storage

agent-browser cookies                     # Get all cookies
agent-browser cookies set name value      # Set cookie
agent-browser cookies clear               # Clear cookies
agent-browser storage local               # Get all localStorage
agent-browser storage local key           # Get specific key
agent-browser storage local set k v       # Set value
agent-browser storage local clear         # Clear all

Network

agent-browser network route \x3Curl>              # Intercept requests
agent-browser network route \x3Curl> --abort      # Block requests
agent-browser network route \x3Curl> --body '{}'  # Mock response
agent-browser network unroute [url]            # Remove routes
agent-browser network requests                 # View tracked requests
agent-browser network requests --filter api    # Filter requests

Tabs & Windows

agent-browser tab                 # List tabs
agent-browser tab new [url]       # New tab
agent-browser tab 2               # Switch to tab
agent-browser tab close           # Close tab
agent-browser window new          # New window

Frames

agent-browser frame "#iframe"     # Switch to iframe
agent-browser frame main          # Back to main frame

Dialogs

agent-browser dialog accept [text]  # Accept dialog
agent-browser dialog dismiss        # Dismiss dialog

JavaScript

agent-browser eval "document.title"   # Run JavaScript

State management

agent-browser state save auth.json    # Save session state
agent-browser state load auth.json    # Load saved state

Example: Form submission

agent-browser open https://example.com/form
agent-browser snapshot -i
# Output shows: textbox "Email" [ref=e1], textbox "Password" [ref=e2], button "Submit" [ref=e3]

agent-browser fill @e1 "[email protected]"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i  # Check result

Example: Authentication with saved state

# Login once
agent-browser open https://app.example.com/login
agent-browser snapshot -i
agent-browser fill @e1 "username"
agent-browser fill @e2 "password"
agent-browser click @e3
agent-browser wait --url "/dashboard"
agent-browser state save auth.json

# Later sessions: load saved state
agent-browser state load auth.json
agent-browser open https://app.example.com/dashboard

Sessions (parallel browsers)

agent-browser --session test1 open site-a.com
agent-browser --session test2 open site-b.com
agent-browser session list

JSON output (for parsing)

Add --json for machine-readable output:

agent-browser snapshot -i --json
agent-browser get text @e1 --json

Debugging

agent-browser open example.com --headed              # Show browser window
agent-browser console                                # View console messages
agent-browser console --clear                        # Clear console
agent-browser errors                                 # View page errors
agent-browser errors --clear                         # Clear errors
agent-browser highlight @e1                          # Highlight element
agent-browser trace start                            # Start recording trace
agent-browser trace stop trace.zip                   # Stop and save trace
agent-browser record start ./debug.webm              # Record from current page
agent-browser record stop                            # Save recording
agent-browser --cdp 9222 snapshot                    # Connect via CDP

Troubleshooting

If the command is not found on Linux ARM64, use the full path in the bin folder.
If an element is not found, use snapshot to find the correct ref.
If the page is not loaded, add a wait command after navigation.
Use --headed to see the browser window for debugging.

Options

--session \x3Cname> uses an isolated session.
--json provides JSON output.
--full takes a full page screenshot.
--headed shows the browser window.
--timeout sets the command timeout in milliseconds.
--cdp \x3Cport> connects via Chrome DevTools Protocol.

Notes

Refs are stable per page load but change on navigation.
Always snapshot after navigation to get new refs.
Use fill instead of type for input fields to ensure existing text is cleared.

Reporting Issues

Skill issues: Open an issue at https://github.com/TheSethRose/Agent-Browser-CLI
agent-browser CLI issues: Open an issue at https://github.com/vercel-labs/agent-browser

安全使用建议

This skill is an instruction-only wrapper that tells an agent how to use the third-party agent-browser CLI. Before installing or invoking it: 1) Verify the upstream package/repo (npm package name, maintainer, GitHub repository) and read its release artifacts — the SKILL.md references vercel-labs/agent-browser but the skill's metadata has mismatched owner/version info, so confirm authenticity. 2) Be aware the CLI can read cookies, localStorage, take screenshots, record video, set headers, and upload files — any of these can leak sensitive data if misused. 3) If you plan to let agents run autonomously, run the CLI in an isolated environment (VM/container) or restrict agent permissions and review command logs. 4) Prefer installing from well-known, trusted sources and inspect the npm package contents before granting it access to sensitive pages or local files.

功能分析

Type: OpenClaw Skill Name: claw-browser-automation Version: 1.0.0 The skill bundle provides a comprehensive interface for 'agent-browser', a headless browser automation tool. It enables high-risk but functional capabilities such as cookie management, session state persistence, and JavaScript execution within the browser context, all of which are clearly aligned with its stated purpose of web automation. The instructions in SKILL.md are transparent, providing both NPM installation and source-based installation from a legitimate Vercel Labs repository (github.com/vercel-labs/agent-browser), and there is no evidence of malicious intent, data exfiltration, or prompt injection.

能力评估

ℹ Purpose & Capability

The skill's name/description (browser automation) matches the instructions (agent-browser CLI commands). Requiring node/npm is appropriate. Minor mismatch: the description highlights a "Rust-based" binary with Node fallback, but SKILL.md only shows npm/pnpm install paths and no Rust build instructions — this may be marketing or reflect a prebuilt Rust binary shipped via npm, but it is worth verifying upstream.

⚠ Instruction Scope

Instructions are focused on web automation (navigate, snapshot, click, fill, screenshots, video, cookies, storage). These actions inherently allow reading site cookies/localStorage, uploading files, setting headers/credentials, and recording sessions — all expected for this purpose but also capable of exposing sensitive data. The SKILL.md does not direct unrelated file/credential reads, but an agent using these commands could exfiltrate data from pages or upload local files if given access.

ℹ Install Mechanism

The skill is instruction-only (no install spec). SKILL.md recommends installing agent-browser from npm or building from GitHub (vercel-labs/agent-browser). Installing an external npm package is normal but carries the usual third-party package risk — you should verify the npm package and GitHub repo before installing.

✓ Credentials

The skill declares no required environment variables or config paths and only needs node/npm binaries. SKILL.md shows runtime commands that accept credentials/headers as parameters (e.g., HTTP basic auth) but these are invoked at runtime rather than requiring new env secrets. No disproportionate environment or credential access is requested by the skill bundle itself.

✓ Persistence & Privilege

always:false and no install-time persistence is requested by the skill. It does not ask to modify other skills or system-wide settings. Autonomous model invocation is allowed (default) — combine this with the CLI's data-access capabilities when deciding whether to allow autonomous runs.

版本历史

v1.0.0

Initial public release of claw-browser-automation. - Fast Rust-based CLI for headless browser automation with Node.js fallback. - Supports navigation, clicking, typing, form filling, snapshots, screenshots, video, and more via structured commands. - Includes powerful selectors: refs, roles, text, labels, and CSS. - Enables programmatic web UI testing, data extraction, and automation from the terminal. - Comprehensive CLI command set for browser control, interaction, and state management.

元数据

Slug claw-browser-automation

版本 1.0.0

许可证 MIT-0

累计安装 1

当前安装数 1

历史版本数 1

常见问题

Claw Browser Automation 是什么？

A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured co... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 128 次。

如何安装 Claw Browser Automation？

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

Claw Browser Automation 是免费的吗？

是的，Claw Browser Automation 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Claw Browser Automation 支持哪些平台？

Claw Browser Automation 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 Claw Browser Automation？

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

Claw Browser Automation