obra/superpowers@subagent-driven-development

Dispatch per-task subagents with two-stage reviews for project plans.

9|2|Updated Mar 18, 2026
One-click install
npx skills add https://github.com/AllBeingsFuture/AllBeingsFuture --skill obra-superpowers-subagent-driven-development-allbeingsfuture
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: obra/superpowers@subagent-driven-development
Source: https://github.com/AllBeingsFuture/AllBeingsFuture/tree/main/electron/embedded-assets/skills/superpowers-subagent-dev
Command: npx skills add https://github.com/AllBeingsFuture/AllBeingsFuture --skill obra-superpowers-subagent-driven-development-allbeingsfuture

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Subagent-Driven Development automates complex task execution by distributing work to fresh subagents per task and enforcing two-stage reviews, enabling faster iteration with isolated context.

Core Features & Use Cases

  • Fresh subagent per task to ensure isolated context and parallel progress
  • Two-stage review: spec compliance followed by code quality review
  • Predefined prompts and templates to automate task dispatch, review, and reporting
  • Works within a single session to maintain continuity for multi-task plans

Quick Start

Dispatch the implementer subagent for a given task and follow the two-stage review workflow to complete each task.

Frequently Asked Questions about obra/superpowers@subagent-driven-development

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

FAQPage Schema
How do I automate code review for multi-task project plans in a single session?

You can automate code review for multi-task plans by dispatching fresh implementer subagents per task and enforcing a two-stage review workflow to ensure spec compliance and code quality within a single session. Predefined prompts handle task dispatch, review, and structured reporting.

What is subagent-driven development and how does it handle task execution?

Subagent-driven development is a workflow orchestration method that distributes work to fresh subagents per task to ensure isolated context. It automates complex task execution by using predefined prompts to dispatch implementer subagents and conduct two-stage reviews for quality and speed.

How do I execute a two-stage code review workflow using subagents?

You execute a two-stage code review by first dispatching an implementer subagent for a task, then running a spec compliance review followed by a code quality review. Predefined prompt templates automate this dispatch and review process to maintain structured reporting.

Can I use automated subagent workflows for independent tasks that need isolated context?

Yes, this subagent workflow is specifically applied to project plans with independent tasks. It instantiates a fresh subagent per task to ensure isolated context and parallel progress, maintaining continuity for multi-task plans within a single session.

What's the best way to orchestrate per-task subagents for rapid development results?

The best way to orchestrate per-task subagents is to use predefined prompt templates that automate task dispatch and enforce two-stage reviews. This approach ensures isolated context for each task and structured reporting, enabling faster iteration and rapid results.

Why does my multi-task plan need fresh subagents for each task instead of a single context?

Fresh subagents per task are needed to ensure isolated context and enable parallel progress. A single context would mix task data, whereas this subagent-driven workflow automates task extraction and dispatches isolated subagents to maintain quality through two-stage reviews.