subagent-driven-development

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

4|1|Updated Feb 3, 2026
One-click install
npx skills add https://github.com/lespaceman/athena-workflow-marketplace --skill subagent-driven-development-lespaceman
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/lespaceman/athena-workflow-marketplace/tree/main/plugins/superpowers/skills/subagent-driven-development
Command: npx skills add https://github.com/lespaceman/athena-workflow-marketplace --skill subagent-driven-development-lespaceman

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps teams orchestrate complex task workflows by dispatching isolated subagents for each task, ensuring high quality through a two-stage review process before moving to the next task.

Core Features & Use Cases

  • Dispatch a fresh subagent per task to isolate context and avoid cross-contamination.
  • Enforce a two-stage review: spec compliance first, then code quality.
  • Gate progress between tasks until reviews pass.
  • Works with plan-writing and plan-execution workflows to handle both serial and parallel task sets.

Quick Start

Load the implementation plan and deploy the first subagent to begin executing tasks.

Frequently Asked Questions about 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 independent tasks in an automation workflow?

To isolate context in an automation workflow, dispatch a fresh subagent per task. This prevents cross-contamination of context between independent tasks, ensuring each subagent operates with a clean slate for improved quality and throughput.

What is the best way to validate spec compliance before reviewing code quality?

The best way to validate spec compliance before reviewing code quality is to enforce a two-stage review process. A dedicated spec compliance review runs first, followed by a code-quality review, ensuring both functional and structural standards are met.

How do I gate progress between tasks until reviews pass?

You gate progress between tasks by enforcing review checkpoints within the orchestration workflow. The system holds the progression to the next task until both the spec compliance and code-quality reviews pass successfully.

Can I use isolated subagents for both serial and parallel task sets?

Yes, isolated subagents can be used for both serial and parallel task sets. This orchestration approach integrates with plan-writing and plan-execution workflows to handle multiple independent tasks efficiently.

When do I need staged validation for task execution?

You need staged validation for task execution when working with plans that have multiple independent tasks. Isolation and staged validation improve overall quality and throughput by catching spec and code issues before moving forward.