skills.rest
badaniya
badaniyaCOMMUNITY
Explore all skills by this author →
GitHub

subagent-driven-development

Dispatch a fresh subagent per task and run two-stage reviews.

1|Updated May 15, 2025
Search Tags:#AI agents#plan execution#task orchestration#two-stage review#subagent-driven-development#prompt-driven workflow
One-click install
npx skills add https://github.com/badaniya/.stowed --skill subagent-driven-development-badaniya
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/badaniya/.stowed/tree/main/agents/.agents/skills/subagent-driven-development
Command: npx skills add https://github.com/badaniya/.stowed --skill subagent-driven-development-badaniya

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables executing implementation plans by dispatching a fresh subagent for each task, paired with a two-stage review cycle to ensure spec compliance and code quality. It minimizes context contamination and accelerates iterations within a single session.

Core Features & Use Cases

  • Fresh subagent per task to keep context clean and actions isolated.
  • Two-stage reviews after each task: spec compliance review followed by code-quality review.
  • In-session task orchestration that supports independent tasks and rapid feedback loops for computing or software development plans.

Quick Start

Use this skill by providing a plan containing multiple tasks; the system will automatically spawn subagents per task, run the two-stage reviews, and report results.

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 multiple independent tasks in a single session without context contamination?▼

To execute independent tasks without context contamination, you can use subagent-driven task orchestration. This approach spawns a fresh subagent per task, ensuring isolated context and rapid iteration for software development plans.

What is the best way to ensure spec compliance and code quality during AI agent task execution?▼

The best way to ensure spec compliance and code quality is to implement a two-stage review cycle after each task. This structured review process validates both spec compliance and code quality before finalizing the output.

How does spawning a fresh subagent per task improve prompt-driven workflows?▼

Spawning a fresh subagent per task improves prompt-driven workflows by maintaining clean, isolated context for each action. This enables parallel progress and rapid feedback loops without previous task interference.

Can I use this task orchestration method for plans with dependent tasks?▼

This task orchestration method is designed for plans with multiple independent tasks executed within a single session. It supports parallel progress and structured reviews for independent tasks, not dependent task chains.

When do I need a two-stage review cycle for subagent-driven development?▼

You need a two-stage review cycle for subagent-driven development when executing implementation plans that require strict spec compliance and code quality validation. It accelerates iterations by providing structured, rapid feedback after each isolated task.

Related Skills

Explore More Software Engineering Skills→
involvexinvolvex

subagent-driven-development

Dispatch fresh subagents for independent plan tasks with automated two-stage review per task.

Community
Advanced
HouseofmvpsHouseofmvps
115

subagent-driven-development

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

Community
Advanced
ibleaiblea
4

ireview

Review code quality, architecture, and best practices using specialized agents.

Community
Intermediate
Veloxia-agencyVeloxia-agency

spawn

Coordinate parallel subagents in isolated git worktrees for shared tasks.

Community
Advanced