skills.rest
ajsai47
ajsai47COMMUNITY
Explore all skills by this author →
WebsiteGitHub

subagent-driven-development

Delegate independent implementation tasks to subagents with two-stage review.

11|2|Updated Mar 31, 2026
Search Tags:#workflow#code review#software development#implementation#subagent#task delegation#spec compliance
One-click install
npx skills add https://github.com/ajsai47/holyclaude --skill subagent-driven-development-ajsai47
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/ajsai47/holyclaude/tree/main/skills/workflow/subagent-driven-development
Command: npx skills add https://github.com/ajsai47/holyclaude --skill subagent-driven-development-ajsai47

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the inefficiency, context pollution, and inconsistent quality that come with manually executing multiple independent implementation tasks from a plan, reducing rework from missed requirements or poor code quality.

Core Features & Use Cases

  • Per-Task Subagent Delegation: Assigns each independent task to a fresh, focused subagent with only the required context, preventing context bloat from switching between tasks.
  • Two-Stage Quality Gates: Runs mandatory spec compliance review first (to catch missing or extra work) followed by code quality review (to catch maintainability issues) for every task before marking it complete.
  • Use Case: When executing a 4-task feature plan for a new CLI tool (e.g., hook installation, recovery modes, progress reporting, and JSON output flags), this skill automates task delegation, review loops, and progress tracking to deliver spec-compliant, high-quality code faster than manual execution.

Quick Start

Use the subagent-driven-development skill to execute the 3-task feature plan in docs/plans/new-hook-feature.md, delegating each task to a subagent with two-stage review per 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 independent implementation tasks from a software development plan?▼

Automating independent implementation tasks from a software development plan is achieved by delegating each task to a focused subagent with isolated context. This approach enforces strict spec compliance and consistent code quality while preventing context bloat across multiple steps.

What is two-stage code review in a subagent-driven development workflow?▼

Two-stage code review in a subagent-driven development workflow is a mandatory quality gate that checks spec compliance first, followed by code quality. This process catches missing or extra work before maintainability issues, ensuring high-quality output per task.

How do I prevent context pollution when executing multiple decoupled software development tasks?▼

Preventing context pollution when executing multiple decoupled software development tasks requires per-task subagent delegation. Assigning each task to a fresh subagent with only the required context stops context bloat from switching between implementation steps.

Can I use task delegation and subagents for complex CLI tool feature implementation?▼

Task delegation and subagents can be used for complex CLI tool feature implementation by assigning independent tasks like hook installation and progress reporting to isolated contexts. Model selection aligned to task complexity reduces rework and accelerates delivery.

What's the best way to track progress and ensure spec compliance for delegated coding tasks?▼

Tracking progress and ensuring spec compliance for delegated coding tasks is best handled via TodoWrite and two-stage review. Progress tracking monitors completion, while mandatory spec compliance review verifies that delegated subagent output meets all requirements.

Why does manual execution of multi-task feature plans lead to inconsistent code quality?▼

Manual execution of multi-task feature plans leads to inconsistent code quality due to context pollution and missed requirements from switching between tasks. Automating task delegation with isolated subagent contexts and mandatory review loops reduces this rework.

Related Skills

Explore More Software Engineering Skills→
huidgehuidge
2

subagent-driven-development

Dispatch fresh subagents per task with two-stage spec and quality reviews.

Community
Advanced
WesleyMFrederickWesleyMFrederick

merging-feature-branches-to-main

Squashes Git feature-branch history into a single commit when merging to main.

Community
Basic
AnveioAnveio
1

claude-agent-sdk

Build autonomous coding agents with the Claude Agent SDK for TypeScript.

Community
Advanced
miles990miles990

subagent-driven-development

Dispatch fresh subagents to execute multi-step implementation plans with two-stage reviews.

Community
Advanced