Research Codebase

This is a parallel research orchestrator that breaks down codebase questions into focused sub-tasks, spawns specialized agents to investigate different areas simultaneously, then synthesizes findings into timestamped markdown documents. It reads any mentioned files in full before decomposing work, which matters for context. The skill delegates to purpose-built agents: codebase-locator finds where things live, codebase-analyzer documents how code works, and codebase-online-researcher fetches external docs using llms.txt or markdown-first protocols. Everything goes into a research directory with YAML frontmatter tracking git state and timestamps. Useful when you need to understand how something works across multiple components without manually chasing references, though you're getting documentation, not critique or suggestions for improvement.