skills.rest
mitul-bhatia
mitul-bhatiaCOMMUNITY
Explore all skills by this author →
GitHub

iterative-retrieval

Iteratively retrieve codebase context through a four-phase refinement loop.

Updated Apr 4, 2026
Search Tags:#planning#context#codebase#subagents#retrieval#iterative
One-click install
npx skills add https://github.com/mitul-bhatia/Vibes --skill iterative-retrieval-mitul-bhatia
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: iterative-retrieval
Source: https://github.com/mitul-bhatia/Vibes/tree/main/.github/skills/iterative-retrieval
Command: npx skills add https://github.com/mitul-bhatia/Vibes --skill iterative-retrieval-mitul-bhatia

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

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

  • A four-phase iterative loop (DISPATCH, EVALUATE, REFINE, LOOP) to progressively refine context with feedback.
  • Efficiently identify relevant files, adapt searches, and reduce token usage in agent orchestration.
  • Use cases include spawning subagents requiring codebase context, handling "context too large" failures, and building RAG-like retrieval pipelines.

Quick Start

Initiate an iterative retrieval cycle to gather high-relevance files that cover the required context.

Frequently Asked Questions about iterative-retrieval

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

FAQPage Schema
How do I retrieve relevant codebase context for subagents when the context is too large to fit in a single prompt?▼

Iterative codebase retrieval progressively searches and refines context using a four-phase loop—DISPATCH, EVALUATE, REFINE, and LOOP—to identify relevant files and reduce token usage in agent orchestration.

What is the best way to handle unknown context requirements when spawning subagents in multi-agent workflows?▼

Handling unknown subagent context requires an iterative retrieval cycle that applies relevance scoring and gap identification to progressively gather high-relevance files until the necessary context is covered.

How does iterative retrieval refine context for agent orchestration?▼

Iterative retrieval refines context through a loop that dispatches searches, evaluates relevance scores, identifies context gaps, and refines subsequent searches to ensure safe, deterministic behavior within cycle bounds.

Can I use this iterative retrieval approach to build RAG-like pipelines for codebase files?▼

Building RAG-like retrieval pipelines for codebase files is a supported use case, applying progressive searches and relevance scoring to efficiently retrieve the specific context needed for subagent execution.

What are the limitations of using cycle-bounded control for subagent context retrieval?▼

Cycle-bounded control limits the number of retrieval iterations to ensure deterministic behavior, meaning context gathering stops once cycle limits are reached even if some codebase gaps remain unfilled.

Does iterative codebase retrieval work without external dependencies?▼

Iterative codebase retrieval operates without external dependencies, running its internal four-phase loop directly within the agent workflow to manage context refinement safely.

Related Skills

Explore More Software Engineering Skills→
VenTheZoneVenTheZone
1

iterative-retrieval

Iteratively search and evaluate codebase files to refine context retrieval.

Community
Advanced
flag3flag3
1

iterative-retrieval

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

Community
Basic
GoosLabGoosLab

moai-foundation-context

Manage Claude Code contexts with token budgets and session persistence.

Community
Advanced
Ikram-AlamIkram-Alam

building-rag-systems

Build RAG systems with semantic chunking, incremental indexing, and filtered retrieval.

Community
Advanced