subagent-driven-development

Dispatch fresh subagents for isolated tasks with two-stage reviews.

1|Updated Apr 17, 2026
One-click install
npx skills add https://github.com/ccakmak60/agentforge --skill subagent-driven-development-ccakmak60
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/ccakmak60/agentforge/tree/main/.trae/skills/subagent-driven-development
Command: npx skills add https://github.com/ccakmak60/agentforge --skill subagent-driven-development-ccakmak60

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Execute plans by dispatching fresh subagents per task with a two-stage review process to ensure spec compliance and code quality, preserving context and accelerating iteration.

Core Features & Use Cases

  • Fresh subagent per task to prevent context leakage and keep tasks focused
  • Two-stage reviews: spec compliance followed by code quality
  • Structured, repeatable task orchestration for sequential or parallel execution in the same session

Quick Start

Dispatch an implementer subagent for Task N, then a spec reviewer and a code-quality reviewer to complete the task.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema
How do I orchestrate subagents for independent tasks without context leakage?

Yes, two-stage reviews ensure spec compliance and code quality by dispatching separate spec and code-quality reviewers per task. This structured workflow validates output sequentially before completing isolated execution steps.

What is the best way to execute decomposed plans sequentially in the same session?

Yes, subagent-driven development supports parallel execution within the same session by dispatching fresh subagents to independent tasks. Each task is isolated and reviewed separately, maintaining focus across concurrent operations.

How does strict context isolation improve code quality during task dispatch?

Strict context isolation improves code quality by preventing cross-task contamination. Fresh subagents execute independent tasks with dedicated prompts, ensuring two-stage reviews evaluate only the intended scope without external interference.

When do I need a two-stage review process for subagent task execution?

You need a two-stage review process when executing decomposed plans that require strict spec compliance and high code quality. It validates isolated task outputs sequentially through dedicated spec and code-quality reviewers.