skills.rest
GGEdu
GGEduCOMMUNITY
Explore all skills by this author →
GitHub

iterative-retrieval

Refine subagent context through iterative retrieval across up to three cycles.

Updated Mar 31, 2026
Search Tags:#codebase#subagents#multi-agent#context-management#iterative-retrieval#retrieval-pattern
One-click install
npx skills add https://github.com/GGEdu/claude-god-mode-template --skill iterative-retrieval-ggedu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: iterative-retrieval
Source: https://github.com/GGEdu/claude-god-mode-template/tree/main/docs/patterns/iterative-retrieval
Command: npx skills add https://github.com/GGEdu/claude-god-mode-template --skill iterative-retrieval-ggedu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Iterative retrieval solves the context problem in multi-agent workflows where subagents don't know what context they need until they start working.

Core Features & Use Cases

  • Progressive context gathering: Retrieve and evaluate files in cycles to build relevant context for subagents.
  • Context-gap detection: Identify missing information and guide refinement to fill gaps.
  • Use Case: When spawning subagents that require evolving project context, this pattern yields targeted files to inform behavior.

Quick Start

Start with a broad retrieval query, then iteratively evaluate and refine results, repeating up to three cycles to assemble high-relevance context.

Frequently Asked Questions about iterative-retrieval

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

FAQPage Schema
How do I gather relevant codebase context for subagents when they don't know what files they need?▼

Iterative retrieval progressively gathers codebase context for subagents by cycling through retrieval, evaluation, and refinement to discover relevant files as project needs evolve.

What is the best way to handle context-too-large or missing-context failures in multi-agent workflows?▼

To handle context-too-large or missing-context failures in multi-agent workflows, use an iterative retrieval loop that evaluates retrieved files and refines search queries to fill identified context gaps.

How does the iterative retrieval loop structure work for refining subagent context?▼

The iterative retrieval loop works through four phases: DISPATCH a broad retrieval query, EVALUATE the results for relevance, REFINE queries to fill missing information gaps, and LOOP up to three cycles for high-relevance context.

When do I need progressive context gathering for multi-agent codebase tasks?▼

You need progressive context gathering when spawning subagents that require evolving project context, because subagents often cannot determine what codebase information they need until they start working on their assigned tasks.

Can I use iterative retrieval to identify missing information in codebase searches?▼

Yes, iterative retrieval identifies missing information through context-gap detection, evaluating retrieved files in each cycle and guiding query refinement to target and fill specific information gaps in the codebase.

What are the limitations of using a three-cycle iterative retrieval pattern for context management?▼

The iterative retrieval pattern is limited to three cycles to produce high-relevance context, meaning highly complex codebases with deeply nested dependencies may require additional manual context scoping beyond the supported loop limit.

Related Skills

Explore More Software Engineering Skills→
andrew-starosciakandrew-starosciak
2

iterative-retrieval

Refine subagent context through a four-stage iterative retrieval loop.

Community
Advanced
flag3flag3
1

iterative-retrieval

Guide subagents through a 4-phase retrieval loop to refine information.

Community
Basic
nesbonesbo
53

data-dotnet

Implement EF Core data persistence as a hexagonal architecture adapter.

Community
Advanced
rock-hurock-hu

openspec-new-change

Scaffold a new OpenSpec change with the artifact-driven workflow.

Community
Advanced