iterative-retrieval

Refine codebase context for subagents through iterative retrieval cycles.

11|2|Updated Mar 18, 2018

Search Tags:#context #codebase #subagents #retrieval #orchestration #iterative

Ready to run

npx skills add https://github.com/GiorgioBertolotti/dotfiles --skill iterative-retrieval-giorgiobertolotti

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: iterative-retrieval
Source: https://github.com/GiorgioBertolotti/dotfiles/tree/main/claude/skills/iterative-retrieval
Command: npx skills add https://github.com/GiorgioBertolotti/dotfiles --skill iterative-retrieval-giorgiobertolotti

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Pattern for progressively refining context retrieval to solve the subagent context problem. The Iterative Retrieval Pattern addresses the context gap that arises when subagents are spawned with incomplete knowledge of the codebase, enabling progressively refined context to guide their work.

Core Features & Use Cases

Four-phase loop (DISPATCH, EVALUATE, REFINE, LOOP) that incrementally narrows context.
Applies to code exploration, debugging, and multi-agent task orchestration where context is too large or partially unknown.
Examples include bug-fix context gathering and feature implementation planning across large repositories.

Quick Start

Run iterative retrieval to start with broad context and refine over up to three cycles until high-relevance files are identified.

Frequently Asked Questions about iterative-retrieval

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

FAQPage Schema

How do I provide relevant codebase context to subagents when the repository is too large?▼

Iterative context refinement solves the subagent context problem by progressively narrowing knowledge across up to three cycles. It applies a DISPATCH, EVALUATE, REFINE, and LOOP loop to incrementally filter broad codebase context into high-relevance files, ensuring subagents receive targeted knowledge for tasks like debugging.

What is the best way to orchestrate multi-agent workflows when context is partially unknown?▼

Iterative retrieval narrows context for subagents by applying criteria-driven re-queries within a four-phase loop. Starting with broad context, it evaluates and refines results over up to three cycles, ensuring subagents handling large codebases receive only high-relevance files for their specific tasks.

Can I use iterative retrieval for debugging and feature implementation planning across large repositories?▼

Yes, iterative retrieval handles large codebases by progressively refining context for subagents. It applies to code exploration, debugging, and multi-agent task orchestration, using a four-phase loop with criteria-driven re-queries to narrow context and prioritize high-relevance results over up to three cycles.

How many retrieval cycles does iterative context refinement run before stopping?▼

Iterative context refinement runs up to three cycles to progressively narrow codebase context for subagents. It applies a four-phase loop—DISPATCH, EVALUATE, REFINE, LOOP—using criteria-driven re-queries to prioritize high-relevance files and exclude low-signal data from the knowledge provided.

When should I avoid using iterative retrieval for subagent context?▼

Avoid using iterative retrieval when the codebase is small or the required context is already fully known. The pattern is designed for large codebases or partially unknown context where progressive refinement across multiple cycles is necessary to exclude low-signal files and prioritize high-relevance results.