subagent-driven-development

Dispatch fresh subagents for sequential tasks with two-stage reviews.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/fernandoxavier02/Superpower-Gemini --skill subagent-driven-development-fernandoxavier02
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/fernandoxavier02/Superpower-Gemini/tree/main/skills/subagent-driven-development
Command: npx skills add https://github.com/fernandoxavier02/Superpower-Gemini --skill subagent-driven-development-fernandoxavier02

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Subagent-driven development addresses the challenge of coordinating multiple specialized agents by dispatching a fresh subagent for each task, keeping contexts isolated to prevent cross-task pollution.

Core Features & Use Cases

  • Fresh subagent per task to maintain focused context.
  • Two-stage review workflow after each task: spec compliance followed by code quality.
  • Structured prompts and templates to ensure consistent execution across tasks.

Quick Start

Dispatch a fresh subagent for each task and enforce two-stage reviews after each task.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema
How do I orchestrate subagents for sequential task execution without cross-task context pollution?

Subagent orchestration dispatches a fresh subagent for each task to maintain isolated context. This prevents cross-task pollution by keeping each subagent focused exclusively on its assigned task within a single session.

What is a two-stage review workflow for subagent-driven development?

A two-stage review workflow applies spec-compliance and code-quality reviews sequentially after each task. It uses structured prompt templates to ensure consistent evaluation of subagent output across all dispatched tasks.

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

You enforce reviews by applying spec-reviewer and code-quality-reviewer prompt templates after each task completes. The spec reviewer checks compliance while the code-quality reviewer evaluates implementation standards independently.

Can I run subagent-driven development for sequential tasks within a single session?

Yes, subagent-driven development applies to sequential task execution within a single session. It dispatches fresh subagents per task while maintaining per-task two-stage reviews throughout the entire workflow.

What's the best way to prevent cross-task context pollution when coordinating multiple specialized agents?

Dispatching a fresh subagent for each task prevents cross-task context pollution. This orchestration model keeps contexts isolated, ensuring each specialized agent operates without interference from prior task data.

Do I need structured prompt templates to coordinate subagents for development tasks?

Structured prompt templates are required to ensure consistent execution across tasks. The implementer, spec-reviewer, and code-quality-reviewer templates provide standardized prompts for dispatch, compliance, and quality evaluation stages.