subagent-driven-development

Name: subagent-driven-development
Availability: InStock
Author: ironbob

Dispatch fresh subagents for individual implementation tasks with isolated context.

Updated Mar 21, 2026

Search Tags:#automation #planning #implementation #concurrency #orchestration #subagent #code-review

Ready to run

npx skills add https://github.com/ironbob/SuperPower_light --skill subagent-driven-development-ironbob

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/ironbob/SuperPower_light/tree/main/skills/subagent-driven-development
Command: npx skills add https://github.com/ironbob/SuperPower_light --skill subagent-driven-development-ironbob

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Subagent-driven development provides a structured workflow to execute implementation plans by delegating work to isolated subagents for individual tasks within a single session, preventing context bleed and accelerating delivery.

Core Features & Use Cases

Fresh subagent per task to keep each task's context isolated and reduce cross-task leakage.
Single combined reviewer for non-trivial tasks to ensure consistent quality checks.
Deterministic, sequential execution (concurrency=1) for predictable coordination and easier debugging.

Quick Start

Dispatch an implementer subagent for each task in your plan and review results with a combined reviewer.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema

What is subagent-driven development and how does it help with implementation planning?▼

Subagent-driven development is a workflow that orchestrates implementation plans by dispatching fresh subagents for individual tasks within a single session. It prevents context bleed and accelerates delivery by keeping each task's context isolated.

How do I execute implementation tasks concurrently while ensuring isolated context?▼

You execute tasks by dispatching fresh subagents for individual tasks within your current session. This approach provides controlled parallel-like execution while maintaining isolated context for each task to reduce cross-task leakage.

Can I use a single reviewer to check multiple implementation tasks?▼

Yes, you can use a single combined reviewer for non-trivial tasks. This ensures consistent quality checks across all tasks dispatched to subagents, providing a consolidated final review of the implementation plan results.

Does subagent orchestration support parallel execution of implementation plans?▼

Subagent orchestration uses deterministic, sequential execution with concurrency set to one. This provides predictable coordination and easier debugging rather than true parallel processing, while still enabling controlled parallel-like execution.

When should I not use subagent-driven development for task orchestration?▼

You should avoid subagent-driven development for tasks that are not largely independent. The workflow is designed for largely independent tasks that require isolated context, so tightly coupled tasks may not benefit from this orchestration approach.

What's the best way to handle issues during subagent task implementation?▼

The best way to handle issues is through the clear escalation path provided by the subagent-driven development workflow. When issues arise during task implementation, you can escalate them while maintaining the combined spec and quality reviewer workflow.