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.
Global
mkdir -p ~/.claude/skills/iterative-retrievalProject
mkdir -p .claude/skills/iterative-retrievalSource Repository
Find Skillsvercel-labs/skills
Find and install the perfect skill to extend your AI agent
Microsoft Foundrymicrosoft/azure-skills
Build, deploy, and improve AI agents on Microsoft Foundry from start to finish
Azure Aimicrosoft/azure-skills
Search, transcribe, and analyze with Azure AI tools for smarter apps
Azure Hosted Copilot Sdkmicrosoft/azure-skills
Build, deploy, and manage your Copilot SDK apps on Azure with ease
Triagemattpocock/skills
Triage issues with a state machine driven by clear roles and agent briefs
Handoffmattpocock/skills
Hand off your work to another AI agent with a clear summary
Image Editagentspace-so/runcomfy-agent-skills
Smart router picks the best AI model for your image editing needs
Agentspaceagentspace-so/skills
See your AI agent's live folder from any browser instantly