subagent-development

This is a stub. Replace with actual content.

5|Updated Feb 24, 2026
One-click install
npx skills add https://github.com/mrtolkien/GHOST --skill subagent-development-mrtolkien
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-development
Source: https://github.com/mrtolkien/GHOST/tree/main/prompts/skills/superpowers/subagent-development
Command: npx skills add https://github.com/mrtolkien/GHOST --skill subagent-development-mrtolkien

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Subagents enable structured, isolated task execution within a session, reducing context leakage and ensuring quality via two-stage reviews.

Core Features & Use Cases

  • Fresh per-task agents: Each task runs in a dedicated subagent to avoid cross-task contamination.
  • Two-stage reviews: Spec compliance review followed by code-quality review to ensure correct, high-quality results.
  • Plan-to-execution workflow: Automates breaking a plan into discrete tasks with clear ownership and traceability.

Quick Start

Dispatch a plan with tasks, then spawn a fresh subagent per task and run two-stage reviews

Frequently Asked Questions about subagent-development

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

FAQPage Schema
How do I automate plan-driven development with isolated subagent workflows?

Automate plan-driven development by dispatching dedicated subagents per task to execute complex plans with isolated context. This approach reduces context leakage and ensures quality through sequential spec-compliance and code-quality reviews.

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

A two-stage review workflow for subagent development enforces a sequential spec-compliance review followed by a code-quality review. This ensures independent task execution meets specifications and maintains high code standards before completion.

How do I prevent context leakage between independent development tasks?

Prevent context leakage by dispatching fresh, dedicated subagents per task. This per-task isolation keeps independent development tasks separate, reducing cross-task contamination and maintaining clean execution environments.

Can I use subagent workflows for complex plans with dependent tasks?

Subagent workflows are applicable to plan-driven development where tasks are largely independent. If your complex plan involves heavily dependent tasks, the per-task isolation and two-stage review design may not suit your context.

What is the best way to break a development plan into discrete tasks for subagents?

The best way to break a development plan into discrete tasks is using a plan-to-execution workflow that automates clear ownership and traceability. Each task then spawns a fresh subagent for isolated execution and review.

Why does my subagent workflow fail spec compliance during code reviews?

Spec compliance failures occur when the two-stage review process identifies gaps between task execution and plan specifications. The sequential review enforces spec compliance before proceeding to the final code-quality check.