agent▌

Terminal-based RSS/Atom feed reader with discovery, search, and OPML import/export. \n \n Discover feeds from any website, subscribe to feeds with optional timeout configuration, and read articles from single or multiple feeds with caching and parallel fetching \n Search across all subscribed feeds locally or discover new feeds via web search (agent-built-in or Exa API) with auto-subscribe and read options \n Clean up broken and duplicate feeds, import/export subscriptions via OPML, and manage f

Extract a Malaysian real-estate agent's display name, full mobile phone (E.164), and email from any EdgeProp.my agent profile or listing page by parsing the inlined Next.js __NEXT_DATA__ payload — bypasses the UI's masked phone and email-form gateway.

Discovers and invokes agent skills for effective task management in engineering workflows.

Self-improving browser automation via the auto-research loop, iteratively enhancing navigation skills for specific website tasks.

Multi-agent architectures distribute work across multiple language model instances, each with its own context window. When designed well, this distribution enables capabilities beyond single-agent limits. When designed poorly, it introduces coordination overhead that negates benefits. The critical insight is that sub-agents exist primarily to isolate context, not to anthropomorphize role division.

Trust system reminders as agent progress notifications. Don't poll.

When the user asks to implement something, use implementation agents to preserve main context.

Playwright-based browser automation with element refs and session persistence for AI agents. \n \n Provides 6 core functions: open (navigate + configure), snapshot (refresh element refs), interact (click/fill/drag/upload/scroll), screenshot, execute (JavaScript), and close \n Uses @e ref system for element targeting; refs invalidate after navigation and require re-snapshot to refresh \n Supports video recording with optional cursor indicator, proxy routing, file uploads, and drag-and-drop intera

Multi-agent architectures distribute work across multiple agent invocations, each with its own focused context. When designed well, this distribution enables capabilities beyond single-agent limits. When designed poorly, it introduces coordination overhead that negates benefits. The critical insight is that sub-agents exist primarily to isolate context, not to anthropomorphize role division.

When working on the Agents workbench layout, always follow these guidelines: