iterative-retrieval

Iteratively refine retrieved files across DISPATCH, EVALUATE, REFINE, and LOOP phases.

15|2|Updated Feb 12, 2026

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

Ready to run

npx skills add https://github.com/kousukef/forge --skill iterative-retrieval-kousukef

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Addresses the "context problem" in multi-agent workflows by progressively refining retrieved content to ensure subagents receive relevant information without overwhelming them.

Core Features & Use Cases

Four-phase loop: DISPATCH, EVALUATE, REFINE, and LOOP to iteratively improve context.
Context-aware retrieval: balances breadth and relevance to minimize token usage while maximizing usefulness.
Practical applications: adaptable to codebase navigation, RAG-like exploration, and agent orchestration where context matures over time.

Quick Start

Start applying the iterative retrieval pattern to guide subagents toward the right-context files with a few cycles.

Frequently Asked Questions about iterative-retrieval

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

FAQPage Schema

How do I prevent token overrun when passing codebase context to multi-agent subagents?▼

To prevent token overrun in multi-agent workflows, progressively refine retrieved files across multiple phases to provide subagents with a balanced context rather than passing large payloads upfront.

What is the best way to refine context for agent orchestration when the required files are unpredictable?▼

The best way to refine context for unpredictable agent orchestration is applying a deterministic loop that dispatches, evaluates, and refines retrieved content to iteratively converge on the right files.

How does iterative retrieval balance breadth and relevance during codebase navigation?▼

Iterative retrieval balances breadth and relevance by cycling through dispatch, evaluate, refine, and loop phases to filter retrieved content, minimizing token usage while maximizing contextual usefulness for subagents.

Can I use a multi-agent context refinement loop for RAG-like exploration?▼

Yes, you can use this multi-agent context refinement loop for RAG-like exploration, as it progressively matures context across multiple phases to extract relevant information without overwhelming the agent.

Does iterative context refinement require predefined file selections before dispatching subagents?▼

No, iterative context refinement does not require predefined file selections, as it is specifically designed for scenarios where subagents need codebase context that cannot be predicted upfront.

What are the limitations of using progressive context refinement in multi-agent workflows?▼

A limitation of progressive context refinement is the overhead of multiple evaluation cycles, meaning it is less suited for simple retrieval tasks where context requirements are already deterministic and fully predictable.