subagent-dev

Execute development plans with fresh subagents and two-stage reviews.

5|Updated Mar 16, 2026
One-click install
npx skills add https://github.com/yash-gadodia/claude-init --skill subagent-dev-yash-gadodia
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-dev
Source: https://github.com/yash-gadodia/claude-init/tree/main/templates/skills/subagent-dev
Command: npx skills add https://github.com/yash-gadodia/claude-init --skill subagent-dev-yash-gadodia

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the problem of maintaining clear context and focus in task-driven development, especially when working with plans with multiple independent tasks.

Core Features & Use Cases

  • Subagent-Driven Development: Executes implementation plans using fresh subagents per task with two-stage review (spec compliance → code quality).
  • Context Clean Subagents: Ensures that each subagent works with exactly the context it needs, preventing context pollution.
  • Automated Review Process: Includes two-stage review processes for spec compliance and code quality.

Quick Start

Dispatch an implementation subagent with the task details to execute a plan using the subagent-dev skill.

Frequently Asked Questions about subagent-dev

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

FAQPage Schema
How do I maintain context isolation when executing complex development plans?

Maintain context isolation in task-driven development by dispatching fresh subagents for each independent task, ensuring they work only with the exact context needed to prevent pollution.

What is a subagent-driven development workflow?

Subagent-driven development is a workflow that executes implementation plans using fresh subagents per task, followed by an automated two-stage review process for spec compliance and code quality.

How do I automate code review for spec compliance in a multi-task plan?

Automate code review for spec compliance by implementing a two-stage review process that first verifies task specification compliance, then evaluates overall code quality for each subagent execution.

Can I execute independent tasks in isolation without context pollution?

Yes, you can execute independent tasks in isolation by using context-clean subagents that work with precisely the context they need, preventing context pollution across multiple development workflow tasks.

What is the best way to execute multi-task implementation plans?

The best way to execute multi-task implementation plans is using a subagent-driven approach with independent, context-clean subagents, requiring a robust review process to ensure spec compliance and code quality.

Why does context pollution occur in task-driven development?

Context pollution occurs in task-driven development when agents share and accumulate unnecessary context across tasks, which is prevented by dispatching fresh, isolated subagents for each independent task execution.