subagent-driven-development

Execute implementation plan tasks with fresh subagents and two-stage reviews.

2|Updated Apr 11, 2026
One-click install
npx skills add https://github.com/PlazaCC/antes-da-tela --skill subagent-driven-development-plazacc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/PlazaCC/antes-da-tela/tree/main/.agents/skills/subagent-driven-development
Command: npx skills add https://github.com/PlazaCC/antes-da-tela --skill subagent-driven-development-plazacc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It eliminates context pollution and coordination bottlenecks when executing multi‑task implementation plans, ensuring each task is handled in isolation and passes rigorous quality checks.

Core Features & Use Cases

  • Fresh subagent per task: Guarantees clean context for every independent piece of work.
  • Two‑stage review: Automated spec‑compliance review followed by code‑quality review for each task.
  • Plan‑driven workflow: Extracts tasks from a plan, creates TodoWrite entries, and orchestrates subagents end‑to‑end.
  • Use Case: A developer with a feature plan can run this skill to automatically implement, test, and review each feature component without manual context switching.

Quick Start

Execute the subagent-driven-development skill on my implementation plan to automatically complete all tasks with 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 implement a multi-task development plan without context pollution across subagents?

Subagent-driven development executes multi-task implementation plans using fresh subagents, guaranteeing clean context for each independent piece of work and eliminating coordination bottlenecks during isolation.

How to automate spec compliance and code quality reviews for each task in a development session?

You can automate reviews by applying a two-stage process: an automated spec-compliance review followed by a code-quality review for each task handled sequentially in the same development session.

Does subagent-driven development work with git worktrees and test-driven development?

Yes, it integrates directly with git worktrees and test-driven development to orchestrate subagents end-to-end, ensuring tasks pass rigorous quality checks while maintaining isolated workspaces.

What's the best way to execute loosely coupled tasks sequentially in the same session?

The best way is using a plan-driven workflow that extracts loosely coupled tasks from a plan, creates TodoWrite entries, and dispatches fresh subagents to handle each task sequentially.

Why does my subagent dispatch lose spec compliance when handling multiple tasks?

Dispatch loses spec compliance when subagent context is polluted; using fresh subagents per task ensures clean context, preventing coordination bottlenecks and maintaining rigorous quality checks.