Iterative Retrieval

This is a pattern for dealing with the classic multi-agent problem where subagents don't know what context they need until they're already working. Instead of dumping everything or guessing, you run a three-cycle loop: dispatch a broad search, evaluate what's actually relevant, refine your query based on what you learned, repeat. It learns your codebase's terminology on the fly, which is honestly the part that matters most. The 0-1 relevance scoring keeps you from wasting tokens on tangentially related files. If you're orchestrating agents that spawn subagents, or you keep hitting context limit errors because you're sending too much or task failures because you sent too little, this gives you the progressive refinement structure to fix it.

Install to Claude Code

npx -y skills add affaan-m/everything-claude-code --skill iterative-retrieval --agent claude-code