cli-anything-browser — Claude Code skill: features and setup
This skill maps Chrome's Accessibility Tree to a virtual filesystem. Agents navigate pages, inspect elements, and click buttons with standard terminal commands.
npx skills add HKUDS/CLI-Anything --skill cli-anything-browser -a claude-codeWhat cli-anything-browser does
The tool bridges command-line interaction with the DOMShell MCP server. Web accessibility trees turn into virtual directories and files. The agent traverses page structure with fs ls and fs cd, reads text with fs cat, and searches strings via fs grep. Page interactions run through the act group, handling clicks and typing into inputs via element paths like /main/button[0].
Cold starts add 1 to 3 seconds to each standalone command. To avoid this overhead during multi-step runs, the CLI provides a daemon mode via session daemon-start. It maintains a persistent MCP connection across calls. The --json flag formats output into clean JSON objects for agent parsing.
Running Chrome with the DOMShell extension active is mandatory before issuing commands. If Chrome is closed or the extension is missing, MCP calls fail immediately. Your environment also requires Node.js, npx, and Python 3.10+.
What it helps with
- inspect web page accessibility trees using filesystem commands
- click buttons and fill input forms using element paths
- extract structured accessibility trees in JSON format for language models
- remove cold start latency across multi-step browser tasks
Example prompts for the agent
- Open the target page with cli-anything-browser page open <url> and find the button using fs grep
- Run cli-anything-browser session daemon-start and fill the login form with act type
- Inspect the page structure in JSON format using cli-anything-browser --json fs ls /
How to install cli-anything-browser
1Skills CLI (Vercel)
npx skills add HKUDS/CLI-Anything --skill cli-anything-browser -a claude-code2Manually: put the files in place
~/.claude/skills/cli-anything-browser/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/cli-anything-browser/
1Skills CLI (Vercel)
npx skills add HKUDS/CLI-Anything --skill cli-anything-browser -a codex2Manually: put the files in place
.agents/skills/cli-anything-browser/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add HKUDS/CLI-Anything --skill cli-anything-browser -a cursor2Manually: put the files in place
.cursor/skills/cli-anything-browser/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install HKUDS/CLI-Anything cli-anything-browser2Manually: put the files in place
.github/skills/cli-anything-browser/SKILL.md1Skills CLI (Vercel)
npx skills add HKUDS/CLI-Anything --skill cli-anything-browser -a gemini-cli2Platform CLI
gemini skills install https://github.com/HKUDS/CLI-Anything --path skills/cli-anything-browserManually: put the files in place
.devin/skills/cli-anything-browser/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add HKUDS/CLI-Anything --skill cli-anything-browser -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set18
The whole set →Similar
Questions about cli-anything-browser
How do I install cli-anything-browser in Claude Code?
Run npx skills add HKUDS/CLI-Anything --skill cli-anything-browser -a claude-code. Ensure Node.js, npx, and Python 3.10+ are installed.
What does cli-anything-browser do?
It maps Chrome's accessibility tree to a virtual filesystem. Agents browse page elements with cd and ls, inspect nodes with cat, and trigger interactions using click and type.
Why do commands fail with an MCP connection error?
Calls fail if Chrome is not running or lacks the DOMShell extension. Chrome must be open with the extension enabled before executing CLI commands.
Source text
SKILL.md · Apache-2.0
--- 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](https://github.com/apireno/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): ```bash # Install Node.js from https://nodejs.org/ npx --version ``` 2. **Chrome/Chromium** with [DOMShell extension](https://chromewebstore.google.com/detail/domshell-browser-filesy/okcliheamhmijccjknkkplploacoidnp): - Install extension in Chrome - Ensure Chrome is running before using CLI 3. **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 ### Basic Navigation ```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] "[email protected]" 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: 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 - [DOMShell GitHub](https://github.com/apireno/DOMShell) - [CLI-Anything](https://github.com/HKUDS/CLI-Anything) - [Issue #90](https://github.com/HKUDS/CLI-Anything/issues/90) ## 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: - 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: ```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: 1. Using Chrome's guest mode or incognito 2. Clearing cookies between sessions 3. Using separate Chrome profiles for different security contexts
© HKUDS · Apache-2.0 · HKUDS/CLI-Anything