Launch Sub Agent

This is a structured approach to spawning focused sub-agents with automatic model selection. It walks through task analysis, picks between Opus/Sonnet/Haiku based on complexity and output size, optionally loads specialized agent prompts for domains like development or research, then wraps everything in mandatory chain-of-thought reasoning at the start and self-critique verification at the end. The whole point is context isolation so each sub-agent gets a clean window instead of your accumulated conversation history. It's thorough to the point of being prescriptive, with decision trees and verification tables baked in. If you're orchestrating multi-agent workflows and want guardrails around model choice and quality checks, this gives you a repeatable pattern.

Install to Claude Code

npx -y skills add neolabhq/context-engineering-kit --skill launch-sub-agent --agent claude-code