subagent-driven-development

Dispatch implementer, spec reviewer, and code quality reviewer subagents for each task.

27|9|Updated Feb 3, 2026
One-click install
npx skills add https://github.com/datasciencemonkey/claude-code-cli-bricks --skill subagent-driven-development-datasciencemonkey
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/datasciencemonkey/claude-code-cli-bricks/tree/main/.claude/skills/subagent-driven-development
Command: npx skills add https://github.com/datasciencemonkey/claude-code-cli-bricks --skill subagent-driven-development-datasciencemonkey

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables teams to execute complex implementation plans by coordinating autonomous subagents per task, reducing context-switch overhead and accelerating delivery.

Core Features & Use Cases

  • Two-stage review workflow per task: spec compliance followed by code quality review.
  • Per-task subagent orchestration: implementer, spec reviewer, and code quality reviewer operate in sequence.
  • Self-review and structured task progression to surface and fix issues before moving on.
  • Reusable prompt templates to standardize how subagents are dispatched.

Quick Start

Example: Run the feature plan using subagent-driven development by dispatching an implementer subagent for each task, then a spec reviewer, then a code-quality reviewer, repeating until all tasks are complete.

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 plan execution with subagents for software development?

Automate plan execution by dispatching fresh subagents for each task, using an implementer, spec reviewer, and code quality reviewer in sequence to drive fast, disciplined development. This orchestration reduces context-switch overhead and accelerates delivery.

What is a two-stage code review workflow for autonomous subagents?

A two-stage code review workflow enforces spec compliance followed by code quality review. Each task is handled by a fresh implementer subagent, then reviewed sequentially by spec and code quality reviewer subagents to surface and fix issues before moving on.

How do I standardize subagent prompts for independent development tasks?

Standardize subagent prompts using reusable prompt templates like implementer-prompt.md, spec-reviewer-prompt.md, and code-quality-review-prompt.md. These templates enforce structured verification and iterative fixes for largely independent tasks within same-session workflows.

When should I use subagent-driven development for my feature plan?

Use subagent-driven development for plan-driven, same-session workflows where tasks are largely independent and require structured verification before completion. It is best suited for teams needing to coordinate autonomous subagents per task to accelerate delivery.

How does subagent orchestration reduce context-switch overhead during coding?

Subagent orchestration reduces context-switch overhead by dispatching fresh subagents for each task. The implementer, spec reviewer, and code quality reviewer operate in sequence, ensuring disciplined development without manual context switching between planning and verification.

Can I use subagent-driven development for dependent tasks in the same session?

Subagent-driven development is best suited for largely independent tasks. For dependent tasks in the same session, the structured two-stage review workflow may require iterative fixes that complicate strict task progression and sequential subagent orchestration.