iterative-retrieval

Run a multi-cycle search and evaluation loop to refine codebase context retrieval.

1|Updated Apr 11, 2026

Search Tags:#context #codebase #optimization #agents #retrieval #orchestration

Ready to run

npx skills add https://github.com/its-Basudeba/Care-HMS --skill iterative-retrieval-its-basudeba

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: iterative-retrieval
Source: https://github.com/its-Basudeba/Care-HMS/tree/main/.agent/skills/iterative-retrieval
Command: npx skills add https://github.com/its-Basudeba/Care-HMS --skill iterative-retrieval-its-basudeba

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the context problem in multi-agent workflows where subagents lack sufficient information to perform tasks, preventing both context-limit overflows and incomplete task execution.

Core Features & Use Cases

Progressive Context Refinement: Uses a 4-phase loop (Dispatch, Evaluate, Refine, Loop) to narrow down relevant codebase information.
Terminology Discovery: Automatically learns project-specific naming conventions and patterns during the retrieval process.
Use Case: When tasked with fixing a complex bug in an unfamiliar codebase, use this Skill to iteratively search for relevant files, evaluate their relevance, and refine the search criteria until the agent has the exact context needed to implement the fix.

Quick Start

Use the iterative-retrieval skill to gather context for the task of fixing the authentication token expiry bug by running the retrieval loop with a maximum of three cycles.

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 subagents when the initial codebase context is insufficient?▼

Optimizing context retrieval for subagents requires a multi-cycle search and evaluation loop that systematically evaluates file relevance and dynamically refines search patterns to ensure high-quality context injection.

What is progressive context refinement and how does it work for codebase exploration?▼

Progressive context refinement is a 4-phase loop—Dispatch, Evaluate, Refine, and Loop—that narrows down relevant codebase information by iteratively discovering and assessing file relevance during the retrieval process.

How do I prevent context-limit overflows when fixing complex bugs in an unfamiliar codebase?▼

Preventing context-limit overflows involves iteratively searching for relevant files, evaluating their relevance, and refining search criteria until the agent has the exact context needed to implement the fix.

When do I need iterative retrieval for multi-agent workflows?▼

Iterative retrieval is needed in multi-agent workflows when subagents lack sufficient information to perform tasks, which prevents both context-limit overflows and incomplete task execution.

Does iterative retrieval automatically learn project-specific naming conventions during codebase search?▼

Iterative retrieval does automatically learn project-specific naming conventions and patterns during the retrieval process through its built-in terminology discovery mechanism.

What are the limitations of using a fixed search cycle for context discovery in agent orchestration?▼

A fixed search cycle limits dynamic refinement, so the iterative retrieval approach requires systematic evaluation of file relevance and dynamic refinement of search patterns to ensure high-quality context injection.