subagent-driven-development

Dispatch fresh subagents to execute implementation plans with two-stage reviews.

Updated Feb 26, 2026
One-click install
npx skills add https://github.com/haulcommand-max/haul-command --skill subagent-driven-development-haulcommand-max
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/haulcommand-max/haul-command/tree/main/vendor/superpowers/skills/subagent-driven-development
Command: npx skills add https://github.com/haulcommand-max/haul-command --skill subagent-driven-development-haulcommand-max

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Executes implementation plans by dispatching fresh subagents per task, with two-stage reviews after each step to ensure spec compliance and high code quality, all within a single session.

Core Features & Use Cases

  • Fresh subagent per task to prevent context pollution and enable parallel iteration
  • Two-stage review workflow: spec compliance review followed by code quality review
  • End-to-end task orchestration: plan extraction, task dispatch, incremental reviews, and automatic completion signals

Quick Start

Provide your implementation plan and let the system dispatch a fresh subagent for each task to execute, review, and iterate.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema
How do I execute implementation plans with independent subagents?

To execute implementation plans with independent subagents, this Skill dispatches a fresh subagent per task to prevent context pollution, enabling parallel iteration and orchestration within a single session.

What is two-stage code review workflow for task dispatch?

Two-stage code review workflow is an automated verification process that executes spec compliance review followed by code quality review after each task dispatch to ensure high standards without human intervention.

How do I automate spec compliance verification during plan execution?

Automate spec compliance verification by dispatching specialized subagents that incrementally review task execution against the original implementation plan requirements within a single session.

Can I run parallel subagent iteration without human in the loop?

Yes, you can run parallel subagent iteration without human in the loop when your plans contain mostly independent tasks, allowing the system to automatically dispatch and review each step.

When should I use subagent-driven development for plan execution?

Use subagent-driven development for plan execution when your implementation plan contains mostly independent tasks requiring two-stage reviews and you want to avoid context pollution across parallel iterations.