superpowers-subagent-driven-development

Dispatch fresh subagents per task with two-stage spec and code quality reviews.

2|1|Updated Oct 21, 2025
One-click install
npx skills add https://github.com/aldoborrero/agent-kit --skill superpowers-subagent-driven-development
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: superpowers-subagent-driven-development
Source: https://github.com/aldoborrero/agent-kit/tree/main/skills/superpowers/subagent-driven-development
Command: npx skills add https://github.com/aldoborrero/agent-kit --skill superpowers-subagent-driven-development

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Execute implementation plans efficiently by dispatching fresh subagents per task within the same session, reducing context switching and boosting iteration speed.

Core Features & Use Cases

  • Fresh-subagent per task for isolated context
  • Two-stage reviews after each task: spec compliance then code quality
  • End-to-end task orchestration from plan extraction to completion in a live session

Quick Start

Dispatch a new subagent for each task in the current session and begin the two-stage review loops immediately.

Frequently Asked Questions about superpowers-subagent-driven-development

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

FAQPage Schema
How do I isolate context when executing multiple implementation tasks in a single session?

Fresh subagents isolate context by executing each implementation task independently, reducing context leakage and maximizing iteration speed within the same live session.

What is subagent-driven development for task orchestration?

Subagent-driven development is a workflow that dispatches fresh subagents to execute implementation plans, enforcing per-task isolation, two-stage reviews, and prompt-driven orchestration to complete tasks hands-off.

How do I automate spec compliance and code quality reviews after each task?

You automate reviews by running a two-stage loop using spec-reviewer and code-quality-reviewer prompts, enforcing structured checks before moving to the next dispatched task.

When should I use a subagent workflow for task dispatch?

Use subagent task dispatch when tasks are largely independent and require structured, hands-off reviews, allowing you to maximize speed and reduce context switching across an implementation plan.

Can I orchestrate independent tasks without context bleeding into subsequent steps?

Yes, per-task isolation prevents context bleeding by dispatching fresh subagents for each independent task, followed by staged reviews to ensure spec compliance before proceeding.