跳到正文
cccskills
免费在 GitHub 公开

cli-anything-browser

Automate browser tasks by exploring Chrome pages like folders. Agents can list page elements, read and search text, click controls, and fill forms through commands, with structured output and a persistent connection mode.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Browser automation CLI using DOMShell MCP server. Maps Chrome's Accessibility Tree to a virtual filesystem for agent-native navigation.

查看安装方法

适用场景

  • Explore page structure and read content
  • Find text and click matching page elements
  • Enter text into forms
  • Run repeated browser commands over a persistent connection

包含的文件(1)

  • SKILL.md6.0 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

cli-anything-browser

A command-line interface for browser automation using DOMShell's MCP server. Navigate web pages using filesystem commands: ls, cd, cat, grep, click.

Installation

Prerequisites

  1. Node.js and npx (for DOMShell MCP server):

    # Install Node.js from https://nodejs.org/
    npx --version
    
  2. Chrome/Chromium with DOMShell extension:

    • Install extension in Chrome
    • Ensure Chrome is running before using CLI
  3. Python 3.10+

Install CLI

cd browser/agent-harness
pip install -e .

Command Groups

page — Page Navigation

  • page open <url> — Navigate to URL
  • page reload — Reload current page
  • page back — Navigate back in history
  • page forward — Navigate forward in history
  • page info — Show current page info

fs — Filesystem Commands (Accessibility Tree)

  • fs ls [path] — List elements at path
  • fs cd <path> — Change directory
  • fs cat [path] — Read element content
  • fs grep <pattern> [path] — Search for text pattern
  • fs pwd — Print working directory

act — Action Commands

  • act click <path> — Click an element
  • act type <path> <text> — Type text into input

session — Session Management

  • session status — Show session state
  • session daemon-start — Start persistent daemon mode
  • session daemon-stop — Stop daemon mode

Usage Examples

Basic Navigation

# Open a page
cli-anything-browser page open https://example.com

# Explore structure
cli-anything-browser fs ls /
cli-anything-browser fs cd /main
cli-anything-browser fs ls

# Go back to root
cli-anything-browser fs cd /

Search and Click

cli-anything-browser fs grep "Login"
cli-anything-browser act click /main/button[0]

Form Fill

cli-anything-browser act type /main/input[0] "user@example.com"
cli-anything-browser act click /main/button[0]

JSON Output

cli-anything-browser --json fs ls /

Daemon Mode (Faster Interactive Use)

# Start persistent connection
cli-anything-browser session daemon-start

# Run commands (uses persistent connection)
cli-anything-browser fs ls /
cli-anything-browser fs cd /main

# Stop daemon when done
cli-anything-browser session daemon-stop

Interactive REPL

cli-anything-browser

Path Syntax

DOMShell uses a filesystem-like path for the Accessibility Tree:

/                           — Root (document)
/main                       — Main landmark
/main/div[0]                — First div in main
/main/div[0]/button[2]      — Third button in first div
  • Array indices are 0-based: button[0] is the first button
  • Use .. to go up one level
  • Use / for root

Agent-Specific Guidance

JSON Output for Parsing

All commands support --json flag for machine-readable output:

cli-anything-browser --json fs ls /

Returns:

{
  "path": "/",
  "entries": [
    {"name": "main", "role": "landmark", "path": "/main"}
  ]
}

Error Handling

The CLI provides clear error messages for common issues:

  • npx not found: Install Node.js from https://nodejs.org/
  • DOMShell not found: Run npx @apireno/domshell --version
  • MCP call failed: Install DOMShell Chrome extension

Check is_available() return value before running commands.

Daemon Mode for Efficiency

For agent workflows with multiple commands, use daemon mode:

  1. Start daemon: cli-anything-browser session daemon-start
  2. Run commands: Each command reuses the MCP connection
  3. Stop daemon: cli-anything-browser session daemon-stop

This avoids the 1-3 second cold start overhead for each command.

Links

Security Considerations

IMPORTANT: When using this CLI with AI agents, be aware of the following security considerations:

URL Restrictions

The browser harness validates all URLs before navigation:

  • Explicit scheme required: URLs must include http:// or https:// scheme (scheme-less URLs like example.com are rejected)
  • Blocked schemes: file://, javascript://, data://, vbscript://, about://, chrome://, and browser-internal schemes
  • Allowed schemes: http:// and https:// only (configurable via CLI_ANYTHING_BROWSER_ALLOWED_SCHEMES)
  • Private network blocking: Optional via CLI_ANYTHING_BROWSER_BLOCK_PRIVATE=true (disabled by default)

DOM Content Risks

The Accessibility Tree includes all visible and hidden elements on a page. Malicious websites could:

  • Craft ARIA labels with manipulative text (e.g., "Ignore previous instructions")
  • Use aria-hidden elements to inject content not visible to users
  • Create confusing DOM structures that mislead navigation

Mitigation: When interacting with untrusted websites, consider:

  1. Using the --json flag for structured output that's easier to parse safely
  2. Sanitizing or filtering DOM content before including it in prompts
  3. Limiting navigation to trusted domains

Private Network Access

By default, the browser can access localhost and private networks (192.168.x.x, 10.x.x.x, etc.). To block:

export CLI_ANYTHING_BROWSER_BLOCK_PRIVATE=true
cli-anything-browser page open http://localhost:8080  # Will be blocked

Session Isolation

Multiple browser sessions share the same Chrome instance. Cookies and authentication state may persist across sessions. For sensitive operations, consider:

  1. Using Chrome's guest mode or incognito
  2. Clearing cookies between sessions
  3. Using separate Chrome profiles for different security contexts

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Build and improve Python command interfaces for GUI applications with OpenClaw. The skill guides source analysis, command design, testing, and packaging, including interactive sessions and structured JSON output for agents.

中文简介正在准备中。当前显示英语简介。

  • Build a command interface for a GUI application
  • Add missing commands to an existing interface
  • Test workflows against the actual application
HKUDS/CLI-Anything5.5万2026年9月22日 更新

Use Reasonix to build or improve a Python command-line interface for existing software. The workflow covers source analysis, interactive commands, JSON output, tests, documentation, and installation checks using the software’s own backend where possible.

中文简介正在准备中。当前显示英语简介。

  • Build command-line access to a GUI application
  • Add missing features to an existing command-line interface
  • Test commands against the actual software backend
HKUDS/CLI-Anything5.5万2026年9月22日 更新

Use Codex to build Python command-line tools for applications with graphical interfaces. Analyze source code, add commands, test against the actual software, validate packaging and documentation, and discover tools already generated or installed.

中文简介正在准备中。当前显示英语简介。

  • Build a command-line tool from application source code
  • Extend an existing tool with more commands
  • Test behavior against the actual application
HKUDS/CLI-Anything5.5万2026年9月22日 更新

Inspect and edit 3MF files for 3D printing. Detect cylindrical holes, change their diameters, repair mesh issues, and compare files while preserving BambuStudio and PrusaSlicer metadata when repacking the edited file.

中文简介正在准备中。当前显示英语简介。

  • Detect cylindrical holes and check their diameters
  • Resize selected holes to a target diameter
  • Repair degenerate faces and duplicate vertices
HKUDS/CLI-Anything5.5万2026年9月22日 更新

Manage AdGuard Home network filtering from the command line. Update blocklists, register devices, configure DNS rules that map names to addresses, and inspect query logs and statistics through the AdGuard Home REST API.

中文简介正在准备中。当前显示英语简介。

  • Adding and refreshing ad-blocking filter lists
  • Mapping local domain names to IP addresses
  • Registering devices and managing fixed address assignments
HKUDS/CLI-Anything5.5万2026年9月22日 更新

Generate slides, documents, websites, and diagrams from natural language prompts through AnyGen OpenAPI. Manage reference uploads, check generation progress, and download finished files using commands with structured output for AI agents.

中文简介正在准备中。当前显示英语简介。

  • Generate slides or documents from written instructions
  • Upload reference files for a generation task
  • Check generation progress and download finished files
HKUDS/CLI-Anything5.5万2026年9月22日 更新

查看 HKUDS 的全部技能

报告此技能的问题