subagent-driven-development

Split implementation plans into tasks and assign fresh subagents with two-stage reviews.

1|Updated Apr 7, 2026
One-click install
npx skills add https://github.com/han-so1omon/ikam --skill subagent-driven-development-han-so1omon
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/han-so1omon/ikam/tree/main/skills/subagent-driven-development
Command: npx skills add https://github.com/han-so1omon/ikam --skill subagent-driven-development-han-so1omon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Subagent-driven development helps teams execute lengthy plans by distributing work to isolated subagents for each task, reducing context leakage and enabling faster iteration.

Core Features & Use Cases

  • Fresh subagent per task with a two-stage review process (spec compliance, then code quality)
  • Isolated task execution and structured prompts to maintain consistency
  • Suitable for decomposed plans requiring rapid, parallel progress

Quick Start

Dispatch a fresh subagent for each task in my plan and enforce two-stage reviews after every 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 execute complex implementation plans using subagents?

You can execute complex implementation plans by splitting them into independent tasks and dispatching a fresh subagent for each task to carry out the work in isolation.

What is a two-stage review process for code quality and spec compliance?

A two-stage review process checks completed subagent tasks first for spec compliance and then for code quality, ensuring high-quality outcomes and preventing context leakage during development.

How do I prevent context leakage when dispatching multiple coding tasks?

To prevent context leakage, assign a fresh subagent per task and use structured prompt templates for implementers and reviewers to maintain consistency and isolation across parallel work.

Can I use structured prompts to automate plan execution and task dispatch?

Yes, you can automate plan execution by using a guided prompt framework with templates for implementers and reviewers, dispatching isolated subagents to enable rapid parallel progress.

Does subagent-driven development require specific dependencies to run?

No, subagent-driven development requires no external dependencies, allowing you to directly split plans and assign fresh subagents for isolated task execution and two-stage reviews.

When should I use isolated subagents for task execution instead of a single agent?

Use isolated subagents for task execution when handling lengthy, decomposed plans that require rapid parallel progress, structured prompts, and strict two-stage reviews to maintain consistency.