What problem does it solve?
This Skill enables context-efficient delegation by offloading read-only research to subagents, returning a concise digest instead of full traces and ensuring state is preserved.
Core Features & Use Cases
- Read-only delegation: Offloads large, context-heavy analysis to subagents without mutating state.
- Digest output: Returns a structured digest suitable for integration with the main task.
- Triggers and thresholds: Applies rules such as when content to read exceeds 250KB and processing depth > 2 steps.
- Use Case: Ideal for codebase reviews, large-document analyses, and knowledge extraction tasks where full context is expensive to compute.
Quick Start
Provide a MODE: SUBAGENT brief with a clear objective, e.g., MODE: SUBAGENT; GOAL: summarize the dependencies of project/*.py; CONTEXT: minimal prior knowledge.