subagent-driven-development

Coordinate independent subagents to execute implementation plans with spec and code quality reviews.

Updated Feb 21, 2026
One-click install
npx skills add https://github.com/abzhaw/juliaz_agents --skill subagent-driven-development-abzhaw
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/abzhaw/juliaz_agents/tree/main/.superpowers/skills/subagent-driven-development
Command: npx skills add https://github.com/abzhaw/juliaz_agents --skill subagent-driven-development-abzhaw

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinating independent subagents to execute implementation plans within a single session eliminates context-switching and speeds up iteration.

Core Features & Use Cases

  • Fresh subagent per task to ensure clean context
  • Two-stage review workflow: spec compliance followed by code quality
  • Automatic task tracking with TodoWrite and per-task lifecycle
  • Flexible execution modes: same-session sequencing or parallel sessions
  • Works with plan extraction and per-task tasking in a single session

Quick Start

Initiate a plan, extract all tasks, and dispatch a per-task implementer subagent followed by spec and code-quality reviewers within the current session.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema
How do I coordinate subagents to execute a development plan within a single session?

Coordinate subagents by dispatching a fresh implementer per task for clean context, followed by spec and code-quality reviewers. TodoWrite tracks the per-task lifecycle automatically to speed up iteration.

What is the best workflow for automating spec compliance and code quality reviews?

Automate spec compliance and code quality reviews using a two-stage subagent workflow. A dedicated spec reviewer checks requirements, then a code quality reviewer inspects the implementation before the task lifecycle closes.

Can I run parallel subagent sessions for independent implementation tasks?

Yes, you can run parallel subagent sessions. The workflow supports both same-session sequencing and parallel sessions, allowing rapid execution of mostly independent tasks extracted from your development plan.

How do I prevent context-switching when executing multiple coding tasks rapidly?

Prevent context-switching by assigning a fresh subagent to each coding task. This approach ensures clean context per task while maintaining rapid iteration through automated TodoWrite tracking and sequential or parallel execution.

Does plan-driven development work with automated per-task tracking?

Yes, plan-driven development integrates directly with automated per-task tracking. Extract all tasks from your plan, dispatch implementer and reviewer subagents, and TodoWrite manages the lifecycle within your current session.

When should I use independent subagents instead of a single agent for development workflows?

Use independent subagents when your development plan contains mostly independent tasks requiring quick spec and quality reviews. This approach eliminates context-switching and speeds up iteration compared to a single agent.