subagent-driven-development

Coordinate subagent implementation tasks with two-stage spec and code quality reviews.

Updated Apr 5, 2026
One-click install
npx skills add https://github.com/Jhabbig/Habbig --skill subagent-driven-development-jhabbig
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/Jhabbig/Habbig/tree/main/.claude/skills/subagent-driven-development
Command: npx skills add https://github.com/Jhabbig/Habbig --skill subagent-driven-development-jhabbig

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you execute implementation plans without losing focus by splitting work into isolated subtasks, each handled by a fresh subagent with its own context.

Core Features & Use Cases

  • Independent task execution: Break a larger plan into smaller pieces and run them one at a time.
  • Two-stage review: Verify each task first for spec compliance and then for code quality before moving on.
  • Same-session coordination: Keep development moving in one conversation while preserving clean context boundaries.
  • Use case: Ideal for multi-step engineering work where implementation, review, and follow-up fixes must happen in a disciplined sequence.

Quick Start

Use this skill to execute the current implementation plan by dispatching a fresh subagent for each task and reviewing the result in two stages.

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 development plans without losing context in a single session?

Coordinate complex development plans by decomposing work into sequential tasks and dispatching a fresh subagent for each isolated implementation to preserve clean context boundaries.

What is two-stage code review and how does it work for task implementation?

Two-stage code review verifies each completed task first for spec compliance and then for code quality before moving on, ensuring disciplined sequential execution and branch completion checks.

How do I break down a large coding task into independent subtasks for continuous execution?

Break down a large coding task by requiring explicit task breakdown, then run per-task implementation using fresh subagents with isolated context to maintain continuous execution.

Can I use isolated subagents for same-session multi-step engineering work?

Yes, isolated subagents are ideal for same-session multi-step engineering work where implementation, review, and follow-up fixes must happen in a disciplined sequence within one conversation.

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

Avoid subagent-driven development when work cannot be decomposed into explicit sequential tasks or when isolated context and continuous execution are not required for your implementation plan.