Explore

Parallel codebase exploration that spawns 3-5 agents to tackle different angles simultaneously: code structure, data flow, architecture patterns, and health assessment. Best for onboarding to unfamiliar repos or understanding how a specific system works under the hood. It asks upfront what you want to explore (full dive, quick scan, just data flow, or patterns), then adapts agent count based on effort level. Outputs include ASCII visualizations, import graphs, and a scored health report. Uses the memory MCP server to remember findings across sessions. The agent coordination is solid but burns tokens on deep exploration, so save it for when you actually need the full picture rather than a quick grep.