superpowers-subagent-driven-development

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

Updated Dec 16, 2025
One-click install
npx skills add https://github.com/fegome90-cmd/fork_agent --skill superpowers-subagent-driven-development-fegome90-cmd
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: superpowers-subagent-driven-development
Source: https://github.com/fegome90-cmd/fork_agent/tree/main/.kilocode/skills/superpowers-subagent-driven-development
Command: npx skills add https://github.com/fegome90-cmd/fork_agent --skill superpowers-subagent-driven-development-fegome90-cmd

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Execute plan by dispatching fresh subagents per task, with a two-stage review after each: spec compliance review first, then code quality review. This approach enables isolated task execution within the same session, accelerating iteration while preserving quality and traceability.

Core Features & Use Cases

  • Fresh subagent per task: avoids context pollution and enables isolated work streams.
  • Two-stage review: spec compliance followed by code quality checks to ensure correctness and maintainability.
  • In-session orchestration: supports interdependent and parallel tasks with clear handoffs and auditable results.
  • Real-world use: large feature rollouts, complex bug-fix plans, and multi-task campaigns where rapid feedback is critical.

Quick Start

Provide your implementation plan to the controller and start dispatching a fresh subagent per task for automated spec and quality reviews.

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 automate plan execution with subagents while maintaining code quality?

You can automate plan execution by dispatching a fresh subagent per task and enforcing a two-stage review for spec compliance and code quality. This isolates task execution, accelerates iteration, and provides auditable QA gates across interdependent workflows.

What is the two-stage review process for subagent task execution?

A two-stage review process checks spec compliance first, then evaluates code quality after a subagent completes a task. This sequential gating ensures correctness against requirements and maintainability before the workflow advances.

How do I set up in-session orchestration for parallel development tasks?

Set up in-session orchestration by providing an implementation plan, subagent prompts, and a governance layer to the controller to coordinate task dispatch, reviews, and branching. This enables parallel tasks with clear handoffs and auditable results.

When should I use fresh subagents for isolated task execution?

Use fresh subagents for isolated task execution during large feature rollouts, complex bug-fix plans, and multi-task campaigns. This avoids context pollution and enables isolated work streams when rapid feedback is critical.

Does subagent-driven development require a specific governance layer?

Subagent-driven development requires a governance layer to coordinate task dispatch, reviews, and branching alongside an implementation plan and subagent prompts. This layer manages the two-stage review process and orchestrates task execution.