Evaluate readiness and publish to crates.io
RLM-style large-codebase comprehension — build a mental map of any codebase by dispatching sub-agents to explore regions without bloating main context
Multi-source research synthesis — aggregate and compare 3+ sources or any source >5KB using sub-agent dispatch and SharedState
Systematically find blind spots in code, architecture, APIs, and deployment — structured critique that catches what familiarity hides
Interact with the community through GitHub Discussions — reply, share, learn
Safely modify your own source code, test changes, and manage your evolution
Analyze your own source code and capabilities to find bugs, gaps, and improvement opportunities
Read X (Twitter) via xurl — search posts, fetch threads, read profiles, and read long-form articles