subagent-driven-development

Execute development plans by dispatching subagents with two-stage reviews.

Updated Mar 14, 2026
One-click install
npx skills add https://github.com/marcusfelix/barney --skill subagent-driven-development-marcusfelix
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/marcusfelix/barney/tree/main/src/prompts/skills/subagent-driven-development
Command: npx skills add https://github.com/marcusfelix/barney --skill subagent-driven-development-marcusfelix

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines complex development tasks by breaking them down into smaller, manageable units, each handled by a specialized subagent, ensuring focused execution and high-quality results through a rigorous review process.

Core Features & Use Cases

  • Task Decomposition: Breaks down implementation plans into independent tasks.
  • Subagent Delegation: Assigns each task to a fresh, specialized subagent.
  • Two-Stage Review: Implements a mandatory spec compliance review followed by a code quality review for each task.
  • Use Case: Developing a new feature defined by a detailed plan. The skill will dispatch an implementer agent for each task, followed by spec and quality reviewers, ensuring each part of the feature is built correctly and efficiently.

Quick Start

Use the subagent-driven-development skill to execute the implementation plan located at ./plans/new-feature.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 iterative development tasks using subagents?

Iterative development tasks are automated by breaking implementation plans into independent units, dispatching a fresh subagent for each task, and running a two-stage review process for spec compliance and code quality after completion.

What is the best way to execute an implementation plan with automated code review?

Executing an implementation plan with automated code review is best handled by dispatching independent subagents for each task, followed by mandatory spec compliance and code quality review stages to ensure focused execution and high-quality results.

How does subagent-driven development handle blocked or incomplete tasks?

Subagent-driven development handles incomplete tasks by assigning statuses like DONE, DONE_WITH_CONCERNS, NEEDS_CONTEXT, and BLOCKED, escalating issues as necessary when a subagent cannot complete its assigned task.

Can I use git worktrees with subagent-driven task execution?

Git worktrees can be used with subagent-driven task execution, as the skill integrates with git worktrees and TDD principles to manage parallel development branches during the implementation plan execution.

Do I need a detailed implementation plan before using subagent task delegation?

A detailed implementation plan is required before using subagent task delegation, because the skill works by decomposing that plan into independent tasks and assigning each unit to a specialized subagent for focused execution.

Why use a two-stage review process for iterative development?

A two-stage review process for iterative development ensures each task meets spec compliance first, then evaluates code quality separately, maintaining rigorous standards and high-quality results throughout the implementation.