skills.rest
tuantiensiu
tuantiensiuCOMMUNITY
Explore all skills by this author →
GitHub

subagent-driven-development

Dispatch fresh subagents per task with mandatory inter-task code reviews.

1|Updated Jan 10, 2026
Search Tags:#automation#subagent#task orchestration#code-review#development-workflow#plan-execution
One-click install
npx skills add https://github.com/tuantiensiu/todo-app --skill subagent-driven-development-tuantiensiu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/tuantiensiu/todo-app/tree/main/.opencode/skill/subagent-driven-development
Command: npx skills add https://github.com/tuantiensiu/todo-app --skill subagent-driven-development-tuantiensiu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill orchestrates the execution of plans by dispatching a fresh subagent for each task and enforcing code reviews between tasks, enabling fast iteration with quality gates.

Core Features & Use Cases

  • Fresh subagent per task to isolate context and prevent leakage
  • Automatic code reviews between tasks to catch issues early
  • Deterministic, review-driven iteration for plan-based workflows
  • Suitable for sessions with mostly independent tasks that require rapid feedback

Quick Start

Dispatch a plan and begin executing each task by spawning a fresh subagent and reviewing results after every task.

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 task orchestration with code reviews between steps?▼

Task orchestration with inter-task code reviews is automated by dispatching a fresh subagent for each task and enforcing mandatory review gates between them. This enables deterministic, review-driven iteration for plan-based workflows.

How does dispatching a fresh subagent per task prevent context leakage?▼

Dispatching a fresh subagent per task isolates context within that specific task, preventing state or variable leakage from previous operations. This in-session isolation maintains execution integrity across independent plan steps.

What is the best way to execute independent tasks in a plan-based development workflow?▼

The best way to execute independent tasks in a plan-based development workflow is using subagent-driven dispatch with structured review and reporting gates between tasks. This approach enables fast iteration with safety checks.

Can I use subagent-driven development for tasks with heavy dependencies on each other?▼

Subagent-driven development is designed for sessions where tasks are largely independent. It applies to plan-based workflows requiring rapid feedback, making it less suitable for tasks with heavy sequential dependencies.

Does subagent dispatch work within a single session for rapid iteration?▼

Subagent dispatch operates within a single session to execute plan-driven tasks. It spawns isolated subagents per task and applies structured review and reporting workflows between them to enable fast iteration with safety gates.

Related Skills

Explore More Software Engineering Skills→
mindfold-aimindfold-ai
13.8k

trellis-bootstrap

Initialize the Trellis AI workflow system in a new project.

Official
Advanced
azat-ioazat-io
14

implementing

Execute approved implementation plans with step-by-step verification and checkpoints.

Community
Basic
dsifrydsifry
60

subagent-driven-development

Dispatch fresh subagents for each task and review code between tasks.

Community
Advanced
obraobra
41

Subagent-Driven Development

Dispatch a fresh subagent for each task and trigger code review after completion.

Community
Basic