What makes browser-cli notable?

966 downloads. Trust evidence available

How should browser-cli be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

browser-cli

Automate browser tasks from the command line with browser-use, including navigation, interaction, screenshots, tabs, cookies, JavaScript, cloud browsing, and... Skill: browser-cli Owner: zdstudios Summary: Automate browser tasks from the command line with browser-use, including navigation, interaction, screenshots, tabs, cookies, JavaScript, cloud browsing, and... Tags: latest:1.0.0 Version history: v1.0.0 | 2026-04-28T03:43:10.107Z | user Initial public release of the browser-use CLI Skill. - Automate browser tasks from the command line: navigation, form filling, screenshot

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

966

Updated

Oct 12, 2026

Version

1.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 966 downloads reported by the source. Last updated 10/12/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 12, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 12, 2026
Adoption signal: 966 downloadsadoption · observed Oct 12, 2026
Latest release: 1.0.0release · observed Apr 28, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 1.0.0release
Initial public release of the browser-use CLI Skill. - Automate browser tasks from the command line: navigation, form filling, screenshots, JavaScript execution, tab and cookie management. - Supports running locally (headless/headed), connecting to real Chrome profiles, or driving cloud browsers. - Organized commands for navigation, interaction, inspection, session management, cloud API, and tunneling local servers. - Quick installation and health checks with simple commands. - Interactive workflows with persistent daemon processes and session controls.
Observed Apr 28, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s17cm60j7xzpqzdgxp50te4ygn83ykme:browser-cli

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-zdstudios-browser-cli/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

17,075 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

# browser-use CLI Skill

## What This Skill Covers
Use this skill any time you need to automate a browser from the command line using `browser-use`. This includes navigating pages, clicking/typing/filling forms, taking screenshots, running JavaScript, managing tabs, handling cookies, driving cloud browsers, and exposing local servers via tunnels.

---

## Installation

### Prerequisites
| Platform | Requirements |
|----------|-------------|
| macOS    | Python 3.11+ |
| Linux    | Python 3.11+ |
| Windows  | Git for Windows + Python 3.11+ |

### One-line Install (Recommended)
```bash
# macOS / Linux
curl -fsSL https://browser-use.com/cli/install.sh | bash

# Windows (PowerShell)
& "C:\Program Files\Git\bin\bash.exe" -c 'curl -fsSL https://browser-use.com/cli/install.sh | bash'
```

### Manual Install
```bash
uv pip install browser-use
browser-use install   # downloads Chromium
browser-use doctor    # validates setup
```

### Post-Install Health Check
```bash
browser-use doctor   # prints diagnostics + config
browser-use setup    # optional interactive wizard
```

---

## Core Mental Model

The workflow is always:
1. **Open** a page → `browser-use open <url>`
2. **Inspect** the page → `browser-use state` (returns numbered element indices)
3. **Interact** using those indices → `browser-use click 3`, `browser-use input 1 "text"`
4. **Repeat** — the daemon keeps the browser alive between commands (~50ms latency)

A background daemon process starts automatically on first command and stays alive until you `browser-use close`.

---

## Browser Modes

```bash
# Default: headless Chromium (invisible)
browser-use open https://example.com

# Visible window
browser-use --headed open https://example.com

# Use your real Chrome (preserves logins, cookies, extensions)
browser-use connect

# Use a specific Chrome profile
browser-use --profile "Default" open https://gmail.com

# Zero-config cloud browser (requires API key)
browser-use cloud connect

# Connect to existing browser via CDP
browser-use --cdp-url http://localhost:9222 open https://example.com
browser-use --cdp-url ws://localhost:9222/devtools/browser/... state
```

After `connect` or `cloud connect`, all subsequent commands automatically target that browser — no extra flags needed.

---

## All Commands

### Navigation
```bash
browser-use open <url>               # Navigate to URL
browser-use back                     # Go back in history
browser-use scroll down              # Scroll down
browser-use scroll up                # Scroll up
browser-use scroll down --amount 1000  # Scroll by pixel amount
```

### Inspection
```bash
browser-use state                    # Get URL, title, and numbered clickable elements
browser-use screenshot output.png    # Take screenshot to file
browser-use screenshot               # Screenshot as base64 (stdout)
browser-use screenshot --full page.png  # Full-page screenshot
```

### Interaction
```bash
browser-use click <index>            # Click element by index (from sta

_meta.json

{
  "ownerId": "kn77p0ar3y9v6qqckkhj51rgd583z7p5",
  "slug": "browser-cli",
  "version": "1.0.0",
  "publishedAt": 1777347790107
}

skill-card.md

## Description:

Automates browser tasks from the command line with browser-use, including navigation, interaction, screenshots, tabs, cookies, JavaScript, cloud browsing, and local tunneling.

This skill is ready for commercial/non-commercial use.

## Publisher:

[zdstudios](https://clawhub.ai/user/zdstudios)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and automation engineers use this skill to drive browser-use CLI workflows for web navigation, inspection, form interaction, screenshots, JavaScript execution, cookie and tab management, cloud browser sessions, and local app testing through tunnels.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill directs users to run remote installer code.

Mitigation: Install only when the browser-use publisher is trusted; prefer an isolated Python environment and manual installation when stronger review is needed.

Risk: Browser automation can access pages, cookies, and local browser profiles.

Mitigation: Use a dedicated low-privilege browser profile and avoid syncing personal or work profiles.

Risk: Cloud browser and tunnel workflows can expose local services or sensitive browsing state.

Mitigation: Avoid public tunnels for sensitive local apps, and close daemons, tunnels, and cloud browsers when work is complete.

Risk: Diagnostics, screenshots, logs, and exported cookies may contain sensitive data.

Mitigation: Redact diagnostic output and generated files before sharing or storing them outside the trusted workspace.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/zdstudios/skills/browser-cli)
- [Publisher profile](https://clawhub.ai/user/zdstudios)
- [browser-use CLI installer](https://browser-use.com/cli/install.sh)

## Skill Output:

**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]

**Output Format:** [Markdown guidance with inline shell commands, configuration paths, and command recipes]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May include commands that start daemon sessions, use browser profiles, manage cookies, call cloud APIs, or open public tunnels.]

## Skill Version(s):

1.0.0 (source: server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 3d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular