ClawHub Skills Lib

Agent Browser Core — AI Agent Skill | Install, Stats & Docs | ClawHub Skills Lib

🤖 Agent Frameworks

Agent Browser Corev1.0.1

agent-browser-core

codedao12

OpenClaw skill for the agent-browser CLI (Rust-based with Node.js fallback) enabling AI-friendly web automation with snapshots, refs, and structured commands.

latest

Download Package View on ClawHub

Installs (all time)

5

Installs (current)

5

Downloads

1.6K

Stars

3

CreatedFeb 6, 2026

UpdatedFeb 25, 2026

Install & Quick Start

Install via ClawdBot CLI:

clawdbot install codedao12/agent-browser-core

Skill Package6 files

📋SKILL.mdmarkdown

Agent Browser Skill (Core)

Purpose

Provide an advanced, production-ready playbook for using agent-browser to automate web tasks via CLI and structured commands.

Best fit

You need deterministic automation for AI agents.
You want compact snapshots with refs and JSON output.
You prefer a fast CLI with Node.js fallback.

Not a fit

You require a full SDK or custom JS integration.
You must stream large uploads or complex media workflows.

Quick orientation

Read references/agent-browser-overview.md for install, architecture, and core concepts.
Read references/agent-browser-command-map.md for command categories and flags.
Read references/agent-browser-safety.md for high-risk controls and safe mode rules.
Read references/agent-browser-workflows.md for recommended AI workflows.
Read references/agent-browser-troubleshooting.md for common issues and fixes.

Required inputs

Installed agent-browser CLI and browser runtime.
Target URLs and workflow steps.
Session or profile strategy if authentication is required.

Expected output

A clear command sequence and operational guardrails for automation.

Operational notes

Snapshot early, act via refs, then snapshot again after DOM changes.
Use --json for machine parsing and scripting.
Use waits and load-state checks before actions.
Close tabs or sessions when done to release resources.

Safe mode defaults

Do not use eval, --allow-file-access, custom --executable-path, or arbitrary --args without explicit approval.
Avoid network route, set credentials, and cookie/storage mutations unless the task requires it.
Allowlist domains and block localhost or private network targets.

Security notes

Treat tokens and credentials as secrets.
Avoid --allow-file-access unless explicitly required.

🤖

AI Usage Analysis

Generated Mar 1, 2026

AI developersData analystsAutomation engineersintermediate

💡 Application Scenarios

E-commerce Price MonitoringRetail/E-commerce

Automate daily price checks across competitor websites by taking snapshots of product pages and extracting pricing data via refs. Use structured commands to navigate, wait for load states, and output JSON for analysis, enabling AI agents to track market trends without manual intervention.

Financial Data AggregationFinance

Scrape public financial reports or stock data from regulatory websites using snapshots and refs to capture structured tables. Employ JSON output for easy parsing into databases, with safe mode to restrict access to allowed domains and avoid risky mutations.

Content Moderation AuditingTechnology/Social Media

Automate checks on user-generated content platforms by taking snapshots of web pages to detect policy violations. Use refs to highlight specific elements and output results as JSON for review, ensuring deterministic automation with load-state waits for dynamic content.

Real Estate Listing CompilationReal Estate

Gather property listings from multiple real estate websites by automating navigation and snapshot capture. Extract details like price and location via refs, outputting structured JSON for comparison, with session management to handle authentication if required.

Academic Research Data CollectionEducation/Research

Automate the collection of research data from online journals or databases using snapshots to preserve page states. Use refs to target specific sections and output JSON for analysis, with operational guardrails to avoid overloading resources and ensure compliance with terms.

💼 Business Models

SaaS Automation ToolSubscription fees

Offer a subscription-based service where businesses use this skill to automate web tasks like data scraping or monitoring. Revenue comes from tiered pricing based on usage volume, with added value from JSON output integration and support for AI workflows.

Consulting and Integration ServicesService fees

Provide consulting to companies needing custom automation solutions, using this skill to build deterministic workflows for specific industries. Revenue is generated through project-based fees and ongoing maintenance contracts, leveraging the CLI's fast performance.

Data-as-a-Service (DaaS)Data sales and licensing

Use the skill to collect and structure web data at scale, then sell processed datasets to clients in sectors like finance or retail. Revenue streams include one-time sales or recurring licenses, with snapshots and refs ensuring data accuracy and machine-readable output.

💬 Integration Tip

Integrate by calling the CLI from scripts or AI agents, using --json for parsing output and following snapshot-ref-action patterns to handle dynamic web content efficiently.