← Back to Skills Marketplace
peytoncasper

Agent Browser - Stagehand

by peytoncasper · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
9721
Downloads
6
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install agent-browser-stagehand
Description
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.
Usage Guidance
Review this carefully before installing. Use it only in a workspace where broad browser automation is acceptable, avoid logging into sensitive accounts unless you isolate or clear the browser profile, do not rely on it for private/internal sites without explicit controls, and treat downloaded files as untrusted. Also verify the actual npm package/source before running npm install or npm link, because the reviewed artifact did not include the CLI implementation.
Capability Analysis
Type: OpenClaw Skill Name: Developer: Version: Description: OpenClaw Agent Skill The skill provides powerful browser automation capabilities, including full network access (localhost, internal networks), persistent browser profiles that store cookies and potentially saved credentials, and automatic file downloads without user interaction. The agent is explicitly allowed to execute arbitrary Bash commands (SKILL.md). Additionally, the browser is launched off-screen (REFERENCE.md), which can be a form of stealth. While these features are aligned with the stated purpose of browser automation, they present significant security risks if the agent is compromised or misdirected, as they enable broad access and potential data handling without explicit malicious intent within the skill's instructions.
Capability Assessment
⚠ Credentials
The skill automatically switches to remote Browserbase mode when API keys are present, with no user prompt, and the reference states the browser can access localhost and internal networks. That is powerful for the stated purpose but under-scoped for privacy and network-boundary risks.
⚠ Install Mechanism
The setup path instructs running npm install and npm link to create a global browser command, but the inspected artifact contains only Markdown and setup metadata, with no package manifest or CLI source to review for the installed runtime behavior.
⚠ Instruction Scope
The skill tells the agent to run broad natural-language browser actions and documents examples that submit forms, enter passwords, and screenshot authenticated pages, without requiring explicit confirmation before sensitive submissions, credential entry, screenshots, or downloads.
⚠ Persistence & Privilege
The reference documents a persistent .chrome-profile directory, retained cookies/saved passwords across sessions, automatic screenshots, and unrestricted automatic downloads to ./agent/downloads/ with no file type restrictions.
ℹ Purpose & Capability
The stated purpose is coherent: it automates browser navigation, form filling, extraction, screenshots, and web app interaction via Bash-driven CLI commands. Those capabilities are expected for a browser automation skill, but they include high-impact actions such as submitting forms, logging into accounts, downloading files, and interacting with authenticated dashboards.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install agent-browser-stagehand
  3. After installation, invoke the skill by name or use /agent-browser-stagehand
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of the browser skill for Stagehand CLI - Automates web browser interactions using natural language commands via CLI - Automatically selects local Chrome or remote Browserbase environment based on configuration - Supports commands to navigate, interact, extract data, observe elements, take screenshots, and close browser - Includes setup instructions, troubleshooting tips, and mode comparison for local vs remote usage
Metadata
Slug agent-browser-stagehand
Version 1.0.0
License —
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Agent Browser - Stagehand?

Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications. It is an AI Agent Skill for Claude Code / OpenClaw, with 9721 downloads so far.

How do I install Agent Browser - Stagehand?

Run "/install agent-browser-stagehand" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Agent Browser - Stagehand free?

Yes, Agent Browser - Stagehand is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Agent Browser - Stagehand support?

Agent Browser - Stagehand is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Agent Browser - Stagehand?

It is built and maintained by peytoncasper (@peytoncasper); the current version is v1.0.0.

💬 Comments