iterative-retrieval

Implement a multi-cycle search and evaluation loop for codebase context retrieval.

Updated Jul 8, 2026

Search Tags:#context #codebase #rag #multi-agent #retrieval #orchestration

Ready to run

npx skills add https://github.com/nazrulsoftwaredev/NIT_CRM_2 --skill iterative-retrieval-nazrulsoftwaredev

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: iterative-retrieval
Source: https://github.com/nazrulsoftwaredev/NIT_CRM_2/tree/main/.agents/skills/iterative-retrieval
Command: npx skills add https://github.com/nazrulsoftwaredev/NIT_CRM_2 --skill iterative-retrieval-nazrulsoftwaredev

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the context problem in multi-agent workflows where subagents lack the necessary codebase knowledge to perform tasks effectively, preventing both context-limit overflows and information gaps.

Core Features & Use Cases

Progressive Context Refinement: Uses a 4-phase loop (Dispatch, Evaluate, Refine, Loop) to narrow down relevant codebase information.
Intelligent Filtering: Automatically scores file relevance and identifies missing context gaps to optimize token usage.
Use Case: When a subagent is tasked with fixing a complex bug in an unfamiliar codebase, this skill guides the agent to iteratively discover the relevant authentication and session-management files without loading the entire repository into memory.

Quick Start

Activate the iterative-retrieval skill to perform a multi-cycle search for files relevant to the current task while progressively refining the search criteria based on evaluation scores.

Frequently Asked Questions about iterative-retrieval

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I optimize context retrieval for multi-agent systems exploring a large codebase?▼

Optimize context retrieval for multi-agent systems by using a multi-cycle search and evaluation loop that progressively narrows down relevant codebase information through systematic relevance scoring and query refinement.

What is iterative context refinement and when do I need it for codebase exploration?▼

Iterative context refinement is a 4-phase loop—Dispatch, Evaluate, Refine, Loop—used when initial context is insufficient for complex codebase exploration. You need it when subagents lack necessary codebase knowledge to perform tasks effectively.

How to prevent context-limit overflows when a subagent searches an unfamiliar codebase?▼

Prevent context-limit overflows by using intelligent filtering that automatically scores file relevance and identifies missing context gaps, optimizing token usage while avoiding loading the entire repository into memory.

Does iterative retrieval work for fixing complex bugs across unfamiliar codebase files?▼

Yes, iterative retrieval works for complex bug fixing in unfamiliar codebases by guiding a subagent to iteratively discover relevant files, like authentication and session-management modules, through systematic relevance scoring and query refinement.

What are the limitations of using a multi-cycle search loop for agent context gathering?▼

The multi-cycle search loop targets complex codebase exploration tasks where initial context is insufficient or unpredictable. It is less suitable for straightforward retrieval needs where initial context is already predictable and sufficient.