subagent-development

Dispatch subagents for each task and enforce two-stage reviews.

Updated Mar 14, 2026

Search Tags:#code review #development workflow #implementation plan #iterative development #task execution #subagent

Ready to run

npx skills add https://github.com/pramudityad/pi-config --skill subagent-development-pramudityad

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: subagent-development
Source: https://github.com/pramudityad/pi-config/tree/main/skills/superpowers/subagent-development
Command: npx skills add https://github.com/pramudityad/pi-config --skill subagent-development-pramudityad

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill streamlines the execution of complex implementation plans by breaking them down into independent tasks, each handled by a fresh subagent, ensuring focused development and rigorous review.

Core Features & Use Cases

Task Decomposition: Breaks down an implementation plan into discrete, manageable tasks.
Independent Subagent Dispatch: Assigns each task to a new, dedicated subagent to prevent context pollution and ensure focus.
Two-Stage Review: Implements a mandatory two-stage review process for each task: first for spec compliance, then for code quality.
Use Case: When developing a new feature with a detailed plan, this Skill ensures each component is built and reviewed systematically, leading to higher quality code and faster iteration cycles within the same development session.

Quick Start

Use the subagent-development skill to execute the implementation plan found in the attached file 'feature-plan.md'.

Frequently Asked Questions about subagent-development

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

FAQPage Schema

How do I execute an implementation plan using independent subagents?▼

Executing an implementation plan with independent subagents involves dispatching a fresh subagent for each task within your session, ensuring focused development. This approach prevents context pollution by isolating task execution and enforcing a two-stage review process for spec compliance and code quality.

What is the two-stage review process for iterative development?▼

The two-stage review process for iterative development mandates a sequential evaluation of each completed task. It first checks the code for strict spec compliance against the implementation plan, then evaluates the code quality, ensuring high standards before merging the subagent's output.

How do I prevent context pollution when handling multiple development tasks?▼

Preventing context pollution when handling multiple development tasks requires assigning each task to a new, dedicated subagent. This task decomposition strategy ensures each subagent maintains a focused context, systematically building components without interference from other plan segments.

Do I need specific development workflow skills to use subagent task execution?▼

Subagent task execution requires integration with specific development workflow skills for a complete process. You need to combine it with tools for writing-plans, git-worktrees, test-driven-development, and finishing-development to manage plans, isolate code, verify tests, and finalize sessions.

What is the best way to break down a feature plan for focused code review?▼

Breaking down a feature plan for focused code review requires task decomposition into discrete, manageable units. By assigning each unit to an independent subagent, you ensure the two-stage review process evaluates spec compliance and code quality for each component systematically.

Why does my subagent development workflow require a dedicated subagent for each task?▼

A subagent development workflow requires a dedicated subagent for each task to guarantee focused development and rigorous review. This isolation prevents context bleed between tasks, ensuring each component is built and reviewed systematically for higher quality iterative development.