delegation-core

## Table of Contents

- [Overview](#overview)
- [When to Use](#when-to-use)
- [Philosophy](#philosophy)
- [Delegation Flow](#delegation-flow)
- [Quick Decision Matrix](#quick-decision-matrix)
- [Detailed Workflow Steps](#detailed-workflow-steps)
- [1. Task Assessment (`delegation-core:task-assessed`)](#1-task-assessment-delegation-coretask-assessed)
- [2. Suitability Evaluation (`delegation-core:delegation-suitability`)](#2-suitability-evaluation-delegation-coredelegation-suitability)
- [3. Handoff Planning (`delegation-core:handoff-planned`)](#3-handoff-planning-delegation-corehandoff-planned)
- [4. Execution & Integration (`delegation-core:results-integrated`)](#4-execution-integration-delegation-coreresults-integrated)
- [Leyline Infrastructure](#leyline-infrastructure)
- [Service-Specific Skills](#service-specific-skills)
- [Module Reference](#module-reference)
- [Exit Criteria](#exit-criteria)


# Delegation Core Framework

## Overview

A method for deciding when and how to delegate tasks to external LLM services. Core principle: **delegate execution, retain high-level reasoning**.

## When to Use
- Before invoking external LLMs for task assistance.
- When operations are token-heavy and exceed local context limits.
- When batch processing benefits from different model characteristics.
- When tasks require routing between models.

## Philosophy

**Delegate execution, retain reasoning.** Claude handles architecture, strategy, design, and review. External LLMs perform data processing, pattern extraction, bulk operations, and summarization.

## Delegation Flow

1. **Task Assessment**: Classify task by complexity and context size.
2. **Suitability Evaluation**: Check prerequisites and service fit.
3. **Handoff Planning**: Formulate request and document plan.
4. **Execution & Integration**: Run delegation, validate, and integrate results.

## Quick Decision Matrix

| Complexity | Context | Recommendation |
|------------|---------|----------------|
| High | Any | Keep