Agent skill

CLI Anything Browser

Browser automation CLI using DOMShell MCP server. An agent skill from HKUDS/CLI-Anything.

Apache-2.0Auto-check: warningsProductivity & Automation

Install CLI Anything Browser

The automated check flagged lines worth reading first. See the safety section below.

skills CLI

$ npx skills add HKUDS/CLI-Anything --skill cli-anything-browser -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install HKUDS/CLI-Anything cli-anything-browser --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/CLI-Anything.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cli-anything-browser .claude/skills/cli-anything-browser && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "cli-anything-browser" agent skill from https://github.com/HKUDS/CLI-Anything/tree/main/skills/cli-anything-browser into .claude/skills/cli-anything-browser/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cli-anything-browser", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/HKUDS/CLI-Anything/tree/main/skills/cli-anything-browser

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add HKUDS/CLI-Anything --skill cli-anything-browser -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install HKUDS/CLI-Anything cli-anything-browser --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/CLI-Anything.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/cli-anything-browser .agents/skills/cli-anything-browser && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "cli-anything-browser" agent skill from https://github.com/HKUDS/CLI-Anything/tree/main/skills/cli-anything-browser into .agents/skills/cli-anything-browser/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cli-anything-browser", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add HKUDS/CLI-Anything --skill cli-anything-browser -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install HKUDS/CLI-Anything cli-anything-browser --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/CLI-Anything.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/cli-anything-browser .cursor/skills/cli-anything-browser && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "cli-anything-browser" agent skill from https://github.com/HKUDS/CLI-Anything/tree/main/skills/cli-anything-browser into .cursor/skills/cli-anything-browser/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cli-anything-browser", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/HKUDS/CLI-Anything.git --path skills/cli-anything-browser

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add HKUDS/CLI-Anything --skill cli-anything-browser -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install HKUDS/CLI-Anything cli-anything-browser --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/CLI-Anything.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/cli-anything-browser .gemini/skills/cli-anything-browser && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "cli-anything-browser" agent skill from https://github.com/HKUDS/CLI-Anything/tree/main/skills/cli-anything-browser into .gemini/skills/cli-anything-browser/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cli-anything-browser", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install HKUDS/CLI-Anything cli-anything-browser

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add HKUDS/CLI-Anything --skill cli-anything-browser -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/CLI-Anything.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/cli-anything-browser .github/skills/cli-anything-browser && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "cli-anything-browser" agent skill from https://github.com/HKUDS/CLI-Anything/tree/main/skills/cli-anything-browser into .github/skills/cli-anything-browser/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cli-anything-browser", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add HKUDS/CLI-Anything --skill cli-anything-browser -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install HKUDS/CLI-Anything cli-anything-browser --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/CLI-Anything.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/cli-anything-browser .opencode/skills/cli-anything-browser && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "cli-anything-browser" agent skill from https://github.com/HKUDS/CLI-Anything/tree/main/skills/cli-anything-browser into .opencode/skills/cli-anything-browser/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cli-anything-browser", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: cli-anything-browser
GitHub stars: 52k
Token cost: ~1.5k tokens
SKILL.md length: 526 words
Files: 1
Skills in repo: 78
Repo updated: Sep 22, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Browser automation CLI using DOMShell MCP server. An agent skill from HKUDS/CLI-Anything.

Works in 3 steps: Node.js and npx (for DOMShell MCP server) → Chrome/Chromium with DOMShell extension → Python 3.10+
Tasks that involve Browser automation
SKILL.md covers Installation, Command Groups, Usage Examples and Path Syntax, plus 3 more sections
Calls npx and pip; reaches nodejs.org

What it does

CLI Anything Browser is an agent skill from HKUDS/CLI-Anything. Browser automation CLI using DOMShell MCP server. Maps Chrome's Accessibility Tree to a virtual filesystem for agent-native navigation.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Productivity & Automation, covering Browser automation and Accessibility. It works with Model Context Protocol. The repository describes itself as: "CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/. The licence is Apache-2.0.

When your agent uses it

Tasks that involve Browser automation
Tasks that involve Accessibility

Example prompts

“/cli-anything-browser”

Requirements

Python 3
Node.js

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

Node.js and npx (for DOMShell MCP server)
Chrome/Chromium with DOMShell extension
Python 3.10+

What it can do on your machine

Read from SKILL.md and the folder at commit 34f5195. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- npx
- pip
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- nodejs.org
Also links to:
- github.com
- chromewebstore.google.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

CLI Anything Browser loads about 1.5k tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 526 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~39
When it runs · the whole SKILL.md, loaded when a task matches: ~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: warnings

The automated check found patterns that need a careful read before installing.

WarningContains instruction-override wording (e.g. “without asking the user”)SKILL.md:193
```
A labels with manipulative text (e.g., "Ignore previous instructions")
```

WarningMentions a credentials file (SSH keys, cloud or package-manager tokens)SKILL.md:210

ultiple browser sessions share the same Chrome instance. Cookies and authentication state may persist across sessions. F

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from HKUDS/CLI-Anything at commit 34f5195, republished under its Apache-2.0 licence (© HKUDS). 526 words, ~1,521 tokens.

Download SKILL.mdSave it as .claude/skills/cli-anything-browser/SKILL.md (or your agent's skills folder).

name: cli-anything-browser
description: Browser automation CLI using DOMShell MCP server. Maps Chrome's Accessibility Tree to a virtual filesystem for agent-native navigation.

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

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

bash

# Install Node.js from https://nodejs.org/
npx --version

Chrome/Chromium with DOMShell extension:
- Install extension in Chrome
- Ensure Chrome is running before using CLI
Python 3.10+

Install CLI

bash

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

bash

# 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

bash

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

Form Fill

bash

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

JSON Output

bash

cli-anything-browser --json fs ls /

Daemon Mode (Faster Interactive Use)

bash

# 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

bash

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:

bash

cli-anything-browser --json fs ls /

Returns:

json

{
  "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:

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

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

Links

Show full SKILL.md (215 more words)Show less

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:

Using the --json flag for structured output that's easier to parse safely
Sanitizing or filtering DOM content before including it in prompts
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:

bash

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:

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

Files

Just SKILL.md in skills/cli-anything-browser of HKUDS/CLI-Anything.

Open the folder on GitHubat commit 34f5195

Compare with similar skills

CLI Anything Browser next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

CLI Anything Browser compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
CLI Anything Browser this skillHKUDS/CLI-Anything	52k	—	~1.5k	Automated safety check: Warn	Apache-2.0	15 days ago
Browser QAaffaan-m/ECC	274k	2 repos	~1k	Automated safety check: Pass	MIT	2 days ago
DocsPrefectHQ/fastmcp	28k	—	~1k	Automated safety check: Pass	Apache-2.0	today
Jarvis Setupethanplusai/jarvis	838	—	~2.5k	Automated safety check: Notes	Custom licence	27 days ago
Gauntletanomalyco/browser-control	438	—	~1.1k	Automated safety check: Pass	MIT	today
Preview Rostradpc/rostra	110	—	~2.3k	Automated safety check: Pass	None	13 days ago

Similar skills

Browser QA
affaan-m/ECC
Run automated post-deploy UI verification with a browser automation MCP (claude-in-chrome, Playwright, or Puppeteer): console-error and Core Web Vitals smoke checks, form and auth-flow interaction…
274k GitHub starsUsed in 2 repos~1k tokens
Frontend & DesignAuto-check passed
Docs
PrefectHQ/fastmcp
Write or revise a page under docs/ for gofastmcp.com. An agent skill from PrefectHQ/fastmcp.
28k GitHub stars~1k tokensUpdated today
Frontend & DesignAuto-check passed
Jarvis Setup
ethanplusai/jarvis
A skill your agent uses when helping someone install, configure, or debug a fresh clone of JARVIS (this repo) — especially "the mic doesn't work", "JARVIS says his language systems are down", any…
838 GitHub stars~2.5k tokensUpdated 27 days ago
Frontend & DesignAuto-check: notes
Gauntlet
anomalyco/browser-control
Run a real-world navigation and capability gauntlet on Browser Control across live websites, fix general DOM/ARIA/CDP root causes, benchmark speed and token efficiency, and finish with a mandatory…
438 GitHub stars~1.1k tokensUpdated today
Productivity & AutomationAuto-check passed
Preview Rostra
dpc/rostra
Use agent-browser to interact with Rostra's live development UI through accessibility snapshots, semantic controls, text entry, and screenshots.
110 GitHub stars~2.3k tokensUpdated 13 days ago
Productivity & AutomationAuto-check passed
Kuri Server
justrach/kuri
Use kuri-server to automate Chrome via HTTP API — navigate pages, get a11y snapshots, interact with elements, capture network traffic (HAR), extract cookies, and bypass bot protection.
365 GitHub stars~6.2k tokensUpdated 2 mo ago
Productivity & AutomationAuto-check: notes

Questions about CLI Anything Browser

What does CLI Anything Browser do?

Browser automation CLI using DOMShell MCP server. An agent skill from HKUDS/CLI-Anything. CLI Anything Browser is an agent skill from HKUDS/CLI-Anything. Browser automation CLI using DOMShell MCP server.

When should I use CLI Anything Browser?

CLI Anything Browser fits situations like: tasks that involve Browser automation; tasks that involve Accessibility.

How do I install CLI Anything Browser in Claude Code?

Run `npx skills add HKUDS/CLI-Anything --skill cli-anything-browser -a claude-code`. Or copy the skill folder (skills/cli-anything-browser in HKUDS/CLI-Anything) into .claude/skills/cli-anything-browser in your project. Claude Code loads it when a task matches its description.

How do I install CLI Anything Browser in Codex?

Run `npx skills add HKUDS/CLI-Anything --skill cli-anything-browser -a codex`. Or copy the skill folder (skills/cli-anything-browser in HKUDS/CLI-Anything) into .agents/skills/cli-anything-browser in your project. Codex loads it when a task matches its description.

Can I use CLI Anything Browser in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HKUDS/CLI-Anything --skill cli-anything-browser -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cli-anything-browser, .gemini/skills/cli-anything-browser, .github/skills/cli-anything-browser and .opencode/skills/cli-anything-browser in your project.

What does CLI Anything Browser need to run?

Going by SKILL.md and its folder, CLI Anything Browser needs the command-line tools its instructions call (npx and pip). Our summary lists: Python 3; Node.js.

Does CLI Anything Browser access the network?

SKILL.md names 3 domains. In commands or code: nodejs.org; the agent is likely to contact it when it follows the instructions. As links in the text: github.com and chromewebstore.google.com. This is read from the text; nothing was executed.

Is CLI Anything Browser safe to install?

Our automated static check of SKILL.md flagged 2 warning(s): contains instruction-override wording (e.g. “without asking the user”); mentions a credentials file (ssh keys, cloud or package-manager tokens). Read the flagged lines before installing; the check is not a guarantee either way.

What licence does CLI Anything Browser use?

CLI Anything Browser is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does CLI Anything Browser use?

About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to CLI Anything Browser?

Skills that share tags, products or a category with CLI Anything Browser: Browser QA (affaan-m/ECC, 274k stars), Docs (PrefectHQ/fastmcp, 28k stars), Jarvis Setup (ethanplusai/jarvis, 838 stars) and Gauntlet (anomalyco/browser-control, 438 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains CLI Anything Browser?

HKUDS (a GitHub organization) maintains it in HKUDS/CLI-Anything, which has 51,644 GitHub stars. The repository holds 78 skills in this directory. The repository was last updated on September 22, 2026.

Source: HKUDS/CLI-Anything on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install CLI Anything Browser

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

cli-anything-browser

Installation

Prerequisites

Install CLI

Command Groups

page — Page Navigation

fs — Filesystem Commands (Accessibility Tree)

act — Action Commands

session — Session Management

Usage Examples

Basic Navigation

Search and Click

Form Fill

JSON Output

Daemon Mode (Faster Interactive Use)

Interactive REPL

Path Syntax

Agent-Specific Guidance

JSON Output for Parsing

Error Handling

Daemon Mode for Efficiency

Links

Security Considerations

URL Restrictions

DOM Content Risks

Private Network Access

Session Isolation

Files

Compare with similar skills

Similar skills

More from HKUDS/CLI-Anything

Related

Questions about CLI Anything Browser

`page` — Page Navigation

`fs` — Filesystem Commands (Accessibility Tree)

`act` — Action Commands

`session` — Session Management