Index Knowledge

This generates AGENTS.md files across your codebase by scoring directories for complexity and creating documentation where it matters most. It fires off parallel explore agents to hunt for patterns, anti-patterns, and conventions, then combines that with bash analysis and LSP symbol data to decide which folders warrant their own knowledge base file. The root always gets full treatment, subdirectories only if they score high enough on metrics like file count, symbol density, and reference centrality. It's built for keeping AI context current without drowning in generic advice. The dynamic agent spawning is clever: bigger projects automatically get more exploration coverage. Use create-new flag to wipe and regenerate from scratch, otherwise it updates existing files and adds new ones where the codebase has grown complex enough to justify them.