subagent-driven-development

Delegate independent tasks to fresh subagents with two-stage spec and quality reviews.

Updated Apr 26, 2026
One-click install
npx skills add https://github.com/dawsonblock/HERMY --skill subagent-driven-development-dawsonblock
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/dawsonblock/HERMY/tree/main/hermes-agent-2026.4.23/skills/software-development/subagent-driven-development
Command: npx skills add https://github.com/dawsonblock/HERMY --skill subagent-driven-development-dawsonblock

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrates task delegation to fresh subagents with independent task execution and two-stage reviews.

Core Features & Use Cases

  • Fresh subagent per task isolates context and prevents cross-task contamination.
  • Two-stage review enforces spec compliance followed by code quality review to ensure alignment and high quality.
  • Structured task workflow guides end-to-end execution from plan intake to completion with explicit feedback loops.
  • Use Case: Ideal for implementing plans where tasks are largely independent and require formal validation before integration.

Quick Start

Dispatch the first implementer subagent for Task 1 and follow with the spec and quality reviews, marking completion after each pass.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema
How do I delegate tasks to subagents for independent code execution?

You can delegate tasks to subagents by dispatching a fresh subagent per task to isolate context, then executing two-stage spec compliance and code quality reviews before marking completion.

What is a two-stage review workflow for code generation?

A two-stage review workflow first enforces spec compliance to verify alignment, then executes a code quality review to ensure high standards before final task completion tracking.

How do I prevent cross-task context contamination during automated task planning?

Prevent cross-task context contamination by dispatching a fresh subagent for every independent task, which isolates execution context and prevents state bleeding across the workflow.

Does this task delegation approach work for plans with dependent tasks?

This delegation approach is designed for plans consisting of independent tasks requiring formal validation, and may not suit workflows with heavy task dependencies or interwoven execution steps.

How to track task completion across delegated subagent iterations?

Track task completion across iterations using the structured end-to-end workflow, which provides explicit feedback loops and completion tracking after passing both spec and quality review stages.