subagent-driven-development

Delegate each task to a fresh subagent with two-stage reviews.

Updated Apr 23, 2026
One-click install
npx skills add https://github.com/Ocean326/Agents --skill subagent-driven-development-ocean326
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/Ocean326/Agents/tree/main/skills/global/subagent-driven-development
Command: npx skills add https://github.com/Ocean326/Agents --skill subagent-driven-development-ocean326

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinating complex, multi-task plans by delegating each task to a fresh subagent, preventing context bleed and accelerating iterative development.

Core Features & Use Cases

  • Fresh subagent per task to maintain isolated context and scalable execution
  • Two-stage review after each task: spec compliance, then code quality
  • Structured workflows for dispatch, rework, and completion within a single session

Quick Start

Delegate the next task to a new subagent and run the two-stage reviews after it completes, then repeat for subsequent tasks.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema
How do I prevent context bleed when coordinating multiple development tasks in a single session?

Delegating each task to a fresh subagent prevents context bleed by isolating execution, ensuring scalable iterative development without prior task interference. This approach maintains clean context windows for each dispatched task.

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

A two-stage review workflow mandates spec compliance and code quality checks after each subagent completes a task. This enforces iterative rework and re-review until acceptance before committing the task output.

How do I handle blocked tasks when dispatching work to subagents?

When dispatching tasks to subagents, blocked tasks follow a structured escalation path. This workflow enforces per-task subagent prompts and provides a defined route to resolve blockers within the session.

Does subagent-driven development require external dependencies or components?

Subagent-driven development requires no external dependencies or components. It operates as a standalone workflow for task dispatch, two-stage review, and iterative development within a single session.

When should I use a fresh subagent per task instead of a single continuous session?

Use a fresh subagent per task for scenarios involving independent tasks requiring isolated context and scalable execution. This approach accelerates iterative development by preventing context bleed between unrelated tasks.