agent-browser-core-1-0-1OpenClaw skill for the agent-browser CLI (Rust-based with Node.js fallback) enabling AI-friendly web automation with snapshots, refs, and structured commands.
Install via ClawdBot CLI:
clawdbot install Lion504/agent-browser-core-1-0-1Provide an advanced, production-ready playbook for using agent-browser to automate web tasks via CLI and structured commands.
references/agent-browser-overview.md for install, architecture, and core concepts.references/agent-browser-command-map.md for command categories and flags.references/agent-browser-safety.md for high-risk controls and safe mode rules.references/agent-browser-workflows.md for recommended AI workflows.references/agent-browser-troubleshooting.md for common issues and fixes.--json for machine parsing and scripting.eval, --allow-file-access, custom --executable-path, or arbitrary --args without explicit approval.network route, set credentials, and cookie/storage mutations unless the task requires it.--allow-file-access unless explicitly required.Generated Mar 1, 2026
Automate daily price checks across competitor websites by navigating to product pages, capturing snapshots, and extracting pricing data via structured commands. Ideal for retail analysts needing deterministic, repeatable workflows without manual browsing.
Scrape public financial reports or stock data from regulatory websites using refs to interact with tables and forms, outputting JSON for further analysis. Suited for fintech firms requiring reliable automation with high accuracy and safety controls.
Automate checks on user-generated content platforms by browsing flagged pages, taking snapshots for review, and logging violations via structured commands. Useful for social media companies ensuring compliance with minimal manual oversight.
Monitor property listing sites for new entries or changes by automating navigation, capturing snapshots with refs, and extracting details like price and availability. Beneficial for real estate agencies tracking market trends efficiently.
Offer a subscription-based service where businesses use this skill to automate web tasks like data scraping or monitoring, with tiered pricing based on usage volume. Revenue streams include monthly fees and premium support for custom workflows.
Provide expert services to integrate this skill into clients' existing AI agent systems, offering customization, training, and ongoing maintenance. Revenue is generated through project-based contracts and hourly consulting rates.
Use the skill to automate collection of specific web data (e.g., market prices, news), process it into structured formats, and sell insights or raw data to clients. Revenue comes from data licensing and API access fees.
💬 Integration Tip
Ensure the agent-browser CLI is installed and test workflows with safe mode defaults before scaling; use JSON output for seamless integration with other tools.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection