subagent-driven-development

Dispatch plan tasks to fresh subagents with two-stage reviews.

16|Updated Apr 19, 2026
One-click install
npx skills add https://github.com/Marwan78888/Neuron-Cli --skill subagent-driven-development-marwan78888
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/Marwan78888/Neuron-Cli/tree/main/scratch/superpowers-main/skills/subagent-driven-development
Command: npx skills add https://github.com/Marwan78888/Neuron-Cli --skill subagent-driven-development-marwan78888

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps teams execute complex implementation plans by delegating tasks to fresh subagents, preventing context leakage and enabling rapid iteration.

Core Features & Use Cases

  • Fresh subagents per task to avoid context leakage
  • Two-stage reviews after each task: spec compliance first, then code quality
  • Works across the current session to coordinate independent tasks without sharing history
  • Supports prompt templates for implementer, spec reviewer, and code quality reviewer to standardize work and ensure quality

Quick Start

Dispatch the plan into the current session and start the first task with a fresh subagent

Frequently Asked Questions about subagent-driven-development

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I prevent context bleed when dispatching parallel tasks in a multi-step plan?

A two-stage review process ensures implementation quality by running spec compliance checks first, followed by code quality reviews. These structured reviews apply after each subagent executes its assigned task to verify both correctness and maintainability.

Does subagent task dispatch work for multi-step plans that require isolated execution?

Yes, subagent task dispatch is designed specifically for multi-step plans requiring isolated execution. It coordinates independent tasks across the current session by spawning fresh agents to prevent context leakage during complex implementations.

How to standardize task orchestration using prompt templates for subagents?

Standardize task orchestration by applying provided prompt templates for the implementer, spec reviewer, and code quality reviewer roles. These templates structure subagent prompts to ensure consistent work and quality across all dispatched tasks.

What is the best way to automate code review and task dispatch for complex implementations?

Automating code review and task dispatch is best handled through structured subagent coordination. This method delegates implementation to fresh subagents and applies a two-stage review process to enforce both spec compliance and code quality automatically.

Why should I use fresh subagents per task instead of sharing session history?

Using fresh subagents per task prevents context leakage that occurs when sharing session history. This isolation enables rapid iteration and accurate task execution by ensuring previous implementation steps do not interfere with current subagent work.