subagent-driven-development

Orchestrate independent subagents to execute implementation plans with per-task reviews.

228|35|Updated Mar 9, 2026
One-click install
npx skills add https://github.com/kaminocorp/hermes-alpha --skill subagent-driven-development-kaminocorp
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/kaminocorp/hermes-alpha/tree/main/hermes-agent/skills/software-development/subagent-driven-development
Command: npx skills add https://github.com/kaminocorp/hermes-alpha --skill subagent-driven-development-kaminocorp

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables orchestration of independent subagents to execute implementation plans by dispatching a fresh subagent per task, ensuring clean context and parallel progress across tasks.

Core Features & Use Cases

  • Fresh subagent per task for isolated reasoning and reduced state bleed.
  • Two-stage review: spec compliance followed by code quality reviews.
  • Parallel task execution with structured, repeatable workflows.
  • Automatic task-to-subagent delegation and status tracking across plans.

Quick Start

Dispatch the first implementation task by invoking a delegate_task with full context for a fresh subagent.

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 in parallel?

You execute parallel implementation tasks by orchestrating independent subagents, dispatching a fresh delegate_task per task to ensure clean context and isolated reasoning across tasks.

What is a fresh subagent workflow for software development?

A fresh subagent workflow dispatches a new delegate_task for each implementation task, ensuring per-task context isolation, two-stage reviews, and traceable task completion across plans.

How do subagents maintain spec compliance during task delegation?

Subagents maintain spec compliance through a two-stage review process that sequentially checks specification compliance followed by code quality reviews across all delegated tasks.

Can I use subagent orchestration for fast iteration on independent tasks?

Subagent orchestration suits tasks that are mostly independent and require fast iteration, applying structured workflows with built-in spec compliance and code-review checkpoints.

Why does dispatching a fresh subagent per task reduce state bleed?

Dispatching a fresh subagent per task reduces state bleed by ensuring per-task context isolation, allowing clean reasoning and parallel progress without shared state interference.

When should I not use parallel subagent orchestration for implementation plans?

Avoid parallel subagent orchestration for tasks that are heavily interdependent, as the workflow applies to mostly independent tasks requiring fast iteration and isolated reasoning.