subagent-driven-development

Dispatch specialized subagents to execute plan tasks with two-stage reviews.

Updated Apr 9, 2026
One-click install
npx skills add https://github.com/jakechen1/echo-research-framework --skill subagent-driven-development-jakechen1
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/jakechen1/echo-research-framework/tree/main/skills-available/subagent-driven-development
Command: npx skills add https://github.com/jakechen1/echo-research-framework --skill subagent-driven-development-jakechen1

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Subagent-driven development addresses the challenge of executing complex implementation plans by dispatching fresh subagents to handle individual tasks and enforcing two-stage reviews to ensure adherence to specifications and code quality.

Core Features & Use Cases

  • Per-task subagents: each task runs in isolation to prevent context pollution and enable fast iteration.
  • Two-stage reviews: spec compliance review first, then code quality review to catch issues early.
  • Structured workflow: plan extraction, task delegation, and finalization with a development branch.

Quick Start

Dispatch the initial implementer subagent with the full plan and start per-task execution with automatic spec and quality reviews.

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 plan execution with subagents for development tasks?

Automating plan execution with subagents involves dispatching fresh subagents to handle individual tasks in isolation, followed by a two-stage review process for spec compliance and code quality before finalizing with a development branch.

What is subagent-driven development and how does it prevent context pollution?

Subagent-driven development is a workflow that dispatches fresh subagents to complete individual tasks in isolation, preventing context pollution and enabling fast iteration through structured per-task delegation and automatic two-stage reviews.

How do I implement two-stage code reviews for automated task delegation?

Implement two-stage code reviews by first running a spec compliance review on the completed task, then running a code quality review to catch issues early before finalizing the development branch.

Does subagent task dispatch work for loosely coupled planning tasks in a single session?

Subagent task dispatch works for independent or loosely coupled planning tasks within a single session where fast iteration and quality checks are beneficial, supporting per-task delegation and in-task questions.

What are the limitations of using subagents for rapid development workflows?

The subagent approach is limited to independent or loosely coupled planning tasks within a single session, meaning tightly coupled tasks requiring extensive shared context may not benefit from this isolation and two-stage review workflow.

Can I ask in-task questions during subagent plan execution?

In-task questions are supported during subagent plan execution, allowing the specialized subagents to handle individual tasks with structured delegation while maintaining spec compliance and code quality reviews.