subagent-driven-development

Dispatch fresh subagents per task with two-stage spec and code reviews.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/namhoangg/agent-starter-kit --skill subagent-driven-development-namhoangg
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/namhoangg/agent-starter-kit/tree/main/cursor/skills/subagent-driven-development
Command: npx skills add https://github.com/namhoangg/agent-starter-kit --skill subagent-driven-development-namhoangg

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Use when executing implementation plans with independent tasks in the current session.

Core Features & Use Cases

  • Fresh subagent per task to ensure isolated context and prevent cross-task leakage
  • Two-stage review workflow: spec compliance review followed by code quality review
  • Self-review and structured task coordination for multi-task plans
  • Ideal for iterative planning sessions and parallel task execution

Quick Start

Initiate by using Subagent-Driven Development to dispatch a fresh subagent for each task and apply two-stage reviews.

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 independent implementation tasks with isolated context using subagents?▼

Executing implementation tasks with isolated context is done by dispatching a fresh subagent per task, preventing cross-task leakage while automating staged spec compliance and code quality reviews before final merge.

What is the best way to automate parallel task execution without cross-task context leakage?▼

Automating parallel task execution without context leakage is best handled by dispatching fresh subagents per task, ensuring each task operates independently within its own isolated context for structured coordination.

Can I use a two-stage review workflow for spec compliance and code quality during development?▼

Yes, you can apply a two-stage review workflow by running a spec compliance review followed by a code quality review, using self-review mechanisms to ensure standards before final merge.

When do I need fresh subagents for iterative planning sessions?▼

You need fresh subagents for iterative planning sessions when executing multi-task implementation plans that require parallel tasking, context separation, and staged reviews to prevent cross-task interference.

Does subagent-driven development work for multi-task plans requiring self-review and final merge?▼

Yes, subagent-driven development works for multi-task plans by providing structured task coordination, applying self-review mechanisms, and executing final merges after passing spec compliance and code quality checks.

What are the limitations of using isolated subagents for development workflow automation?▼

Isolated subagent automation is limited to sessions executing implementation plans with independent tasks, requiring structured coordination and staged reviews to ensure spec compliance and code quality before merge.