subagent-driven-development

Dispatch subagents to implement plan tasks with code reviews between tasks.

1|Updated Mar 4, 2026
One-click install
npx skills add https://github.com/Kuass/kiro-gateway-plus --skill subagent-driven-development-kuass
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/Kuass/kiro-gateway-plus/tree/main/.opencode/skill/subagent-driven-development
Command: npx skills add https://github.com/Kuass/kiro-gateway-plus --skill subagent-driven-development-kuass

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines the implementation of development plans by breaking them into independent tasks, each handled by a fresh subagent, with automated code reviews between tasks to ensure quality and enable rapid iteration.

Core Features & Use Cases

  • Task Decomposition: Executes plans by dispatching a new subagent for each individual task.
  • Automated Code Review: Integrates code review after each task to catch issues early.
  • Fast Iteration: Enables continuous progress within the same session, reducing context switching and manual handoffs.
  • Use Case: When working on a complex feature defined by a plan, use this skill to have subagents implement each part (e.g., API endpoint, UI component, database schema) sequentially, with automated checks after each implementation step.

Quick Start

Use the subagent-driven-development skill to execute the plan located at /path/to/your/plan.md.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema
How do I automate iterative development tasks from an implementation plan?

Automating iterative development tasks is achieved by dispatching independent subagents for each individual task, ensuring sequential implementation within a single session to reduce manual handoffs.

Can I integrate code review into automated task execution for quality assurance?

Integrating code review into automated task execution is supported by running automated checks after each subagent completes its task, catching issues early before proceeding to the next iteration.

What is the best way to decompose a complex feature into independent development tasks?

Decomposing a complex feature is handled by dispatching a new subagent for each specific component like an API endpoint or UI schema, executing them sequentially with automated reviews between tasks.

Do I need a specific plan format to start subagent-driven iterative development?

Subagent-driven iterative development requires a markdown plan file as input, which is parsed to dispatch subagents sequentially and execute the defined implementation tasks automatically.

When should I use subagent dispatching for rapid iteration over manual coding?

Subagent dispatching for rapid iteration is ideal when working on complex features requiring continuous progress within the same session, minimizing context switching and manual handoffs.

What additional skills are required to execute plans with this iterative development approach?

Executing plans with this iterative development approach requires integration with separate skills for plan writing, automated code review, and final branch completion to ensure full quality assurance.