iterative-retrieval
SolidPattern for progressively refining context retrieval to solve the subagent context problem
AI & Automation 552 stars
45 forks Updated 6 days ago MIT
Install
Quality Score: 91/100
Stars 20%
Recency 20%
Frontmatter 20%
Documentation 15%
Issue Health 10%
License 10%
Description 5%
Skill Content
# Iterative Retrieval Pattern
Solves the "context problem" in multi-agent workflows where subagents don't know what context they need until they start working.
## The Problem
Subagents are spawned with limited context. They don't know:
- Which files contain relevant code
- What patterns exist in the codebase
- What terminology the project uses
Standard approaches fail:
- **Send everything**: Exceeds context limits
- **Send nothing**: Agent lacks critical information
- **Guess what's needed**: Often wrong
## The Solution: Iterative Retrieval
A 4-phase loop that progressively refines context:
```
┌─────────────────────────────────────────────┐
│ │
│ ┌──────────┐ ┌──────────┐ │
│ │ DISPATCH │─────▶│ EVALUATE │ │
│ └──────────┘ └──────────┘ │
│ ▲ │ │
│ │ ▼ │
│ ┌──────────┐ ┌──────────┐ │
│ │ LOOP │◀─────│ REFINE │ │
│ └──────────┘ └──────────┘ │
│ │
│ Max 3 cycles, then proceed │
└─────────────────────────────────────────────┘
```
### Phase 1: DISPATCH
Initial broad query to gather candidate files:
```javascript
// Start with high-level intent
const initialQuery = {
patterns: ['src/**/*.ts', 'lib/**/*.ts'],
keywords: ['authentication', 'us...
Details
- Author
- vibeeval
- Repository
- vibeeval/vibecosystem
- Created
- 8 months ago
- Last Updated
- 6 days ago
- Language
- C#
- License
- MIT
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
AI & Automation Listed
iterative-retrieval
Pattern for progressively refining context retrieval to solve the subagent context problem
159 Updated 4 months ago
arabicapp Web & Frontend Listed
iterative-retrieval
Pattern for progressively refining context retrieval when subagents don't know what context they need until they start. Use this skill whenever a subagent or fan-out task must discover relevant files / patterns / terminology on its own, when "send everything" overflows context and "send nothing" starves the agent, or when designing multi-agent retrieval that converges on the right context iteratively.
0 Updated today
sardonyx0827 AI & Automation Listed
iterative-retrieval
Pattern for progressively refining context retrieval to solve the subagent context problem
30 Updated today
nikolanovoselec