AI AGENT ADDONS
AI & Agent Building
5,625installs

Imagine an AI agent that needs to explore your codebase but does not know where to look. This pattern solves that problem with a simple loop. It starts with a broad search and then refines the search based on what it finds. The agent never wastes tokens on irrelevant files. It keeps narrowing down until it has the right context.

This method works for any project where subagents need to find relevant code or information. It stops the common failures of sending too much or too little context. The loop runs up to three times to balance speed and accuracy.

Add Iterative Retrieval skill to your workflow

Global

mkdir -p ~/.claude/skills/iterative-retrieval

Project

mkdir -p .claude/skills/iterative-retrieval

Source Repository

Stars
222,953
Forks
34,145
Watchers
222,953
License
MIT
Last Push
25 days ago
Created
6 months ago