iterative-retrieval
A four-phase iterative retrieval pattern for LLM agents to efficiently gather relevant codebase context.
Install
npx skills add https://github.com/affaan-m/everything-claude-code --skill iterative-retrievalStats
| Total installs | 1,581 |
| Weekly installs | 1.6K |
| GitHub stars | 112.5K |
| First seen | Jan 26, 2026 |
| Source | @affaan-m/everything-claude-code |
Summary
- Four-phase cycle (dispatch, evaluate, refine, loop) that iteratively narrows retrieval to high-relevance files, capping at 3 iterations to balance token usage and context quality
- Scores retrieved files on a 0–1 relevance scale and explicitly identifies missing context gaps to drive the next refinement cycle
- Learns codebase terminology and patterns during the first cycle, improving subsequent searches without requiring upfront knowledge of project conventions
- Designed for spawning subagents on code exploration, bug fixes, and feature implementation tasks where context needs are unpredictable upfront
Tags
Related skills
| Skill | Installs | vs iterative-retrieval |
|---|---|---|
| meta-tags-optimizer | 1,509 | -72 |
| write-a-skill | 1,528 | -53 |
| dbs | 1,633 | +52 |
| tavily-extract | 1,731 | +150 |
| health | 1,742 | +161 |
FAQ
- How many installs does iterative-retrieval have?
- iterative-retrieval has 1,581 total installs and 1.6K installs this week.
- Where is iterative-retrieval hosted?
- iterative-retrieval is published by @affaan-m/everything-claude-code at https://github.com/affaan-m/everything-claude-code.
- How many GitHub stars does iterative-retrieval have?
- iterative-retrieval has 112.5K GitHub stars.
- When was iterative-retrieval first indexed?
- OrangeBot.AI first indexed iterative-retrieval on Jan 26, 2026.
- How do I install iterative-retrieval?
- Run: npx skills add https://github.com/affaan-m/everything-claude-code --skill iterative-retrieval