subagent-driven-development

Dispatch isolated subagents for plan tasks with per-task reviews.

Updated May 19, 2026
One-click install
npx skills add https://github.com/costrict-plugins-repo/anthropic-superpowers --skill subagent-driven-development-costrict-plugins-repo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/costrict-plugins-repo/anthropic-superpowers/tree/main/skills/subagent-driven-development
Command: npx skills add https://github.com/costrict-plugins-repo/anthropic-superpowers --skill subagent-driven-development-costrict-plugins-repo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Use this Skill when executing implementation plans by delegating tasks to isolated, purpose-built subagents, enabling parallel progress, isolated context, and structured reviews.

Core Features & Use Cases

  • Fresh subagent per task to keep context clean and reduce cross-task contamination.
  • Per-task reviews (spec compliance + code quality) and final whole-branch review.
  • Ledger and diff-based handoffs for traceability and safe merges.

Quick Start

Dispatch an implementer subagent for the first plan task and let it proceed, then follow with per-task reviews.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema
How do I orchestrate complex multi-task plans using isolated subagents?

Subagent orchestration dispatches isolated subagents for each plan task to enable parallel progress and structured reviews. It keeps context clean, reduces cross-task contamination, and produces a traceable ledger with a consolidated diffs package.

What is the best way to automate code review across independent implementation tasks?

Automated code review for independent tasks works by applying per-task reviews for spec compliance and code quality, followed by a final whole-branch review. This ensures iterative validation and safe merges using diff-based handoffs.

How do I manage workflow execution for long-running development sessions?

Workflow management for long-running sessions requires per-task review workflows and a final whole-branch review to produce traceable ledgers and safe diffs packages. Fresh subagents handle each isolated task to maintain context integrity.

Can I use isolated subagents for complex projects requiring iterative reviews?

Isolated subagents fit complex, multi-task projects that require independent task execution, iterative reviews, and final consolidation. You need clear task briefs and role-specific prompts to properly dispatch and execute each plan task.

Why use fresh subagents per task instead of a single agent for plan execution?

Fresh subagents per task keep context clean and reduce cross-task contamination during plan execution. Unlike a single agent, this approach enables parallel progress, isolated context handling, and structured per-task reviews for safer merges.

What do I need to prepare before dispatching subagents for task orchestration?

Task orchestration with subagents requires clear task briefs, role-specific prompts, and defined per-task review workflows. You must establish these inputs before dispatching isolated subagents to ensure traceable ledger generation and final consolidation.