subagent-driven-development

Name: subagent-driven-development
Availability: InStock
Author: unclehowell

Execute implementation plans by dispatching fresh subagents for each task.

Updated Sep 1, 2021

Search Tags:#automation #workflow #implementation #delegation #subagent #code-review

Ready to run

npx skills add https://github.com/unclehowell/unclehowell --skill subagent-driven-development-unclehowell

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/unclehowell/unclehowell/tree/main/skills/software-development/subagent-driven-development
Command: npx skills add https://github.com/unclehowell/unclehowell --skill subagent-driven-development-unclehowell

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Implementing large feature plans manually can lead to missed specifications, inconsistent code quality, and context leakage between tasks. This skill automates the execution of independent tasks by spawning fresh subagents and enforcing a two‑stage review process to ensure spec compliance and high‑quality code.

Core Features & Use Cases

Fresh subagent per task eliminates context contamination.
Two‑stage review (spec compliance first, then code quality) guarantees correctness.
Automated dispatch using delegate_task with terminal and file toolsets.
Suitable for software development projects with clear task breakdowns, such as feature implementations, refactoring sprints, or rapid prototyping.

Quick Start

Ask the subagent-driven development skill to execute the plan at 'docs/plans/feature-plan.md'.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema

How do I automate implementation plan execution without context leakage between tasks?▼

Automating implementation plan execution without context leakage is achieved by dispatching a fresh subagent for each independent task. This approach prevents context contamination by isolating task execution and enforcing a two-stage review process for spec compliance and code quality.

What is a two-stage review process for code implementation and spec compliance?▼

A two-stage review process for code implementation applies spec compliance checks first, followed by code quality reviews. This mechanism guarantees correctness by using fresh subagents to independently verify that the output meets specifications and maintains high quality.

How do I dispatch subagents for independent software development tasks?▼

Dispatching subagents for independent software development tasks requires using delegate_task calls equipped with terminal and file toolsets. This automated dispatch method spawns fresh subagents to execute self-contained tasks and run final integration checks.

When do I need fresh subagents for feature implementation plans?▼

Fresh subagents are needed for feature implementation plans when tasks are self-contained and require strict spec compliance and code quality reviews. This approach suits software development projects like refactoring sprints or rapid prototyping where eliminating context contamination is critical.

Does automated subagent dispatch work for refactoring sprints and rapid prototyping?▼

Automated subagent dispatch works for refactoring sprints and rapid prototyping by applying delegate_task calls to execute independent tasks. It utilizes terminal and file toolsets to run spec reviewers, quality reviewers, and final integration checks for these development contexts.

Why does spawning a fresh subagent per task eliminate context contamination?▼

Spawning a fresh subagent per task eliminates context contamination because each independent task executes in isolation. This prevents previous task states from leaking into new implementations, ensuring consistent code quality and strict spec compliance throughout the workflow.