skills.rest
Xza85hrf
Xza85hrfCOMMUNITY
Explore all skills by this author →
GitHub

subagent-driven-development

Orchestrate per-task subagents with isolated contexts and two-stage reviews.

Updated Feb 9, 2026
Search Tags:#automation#planning#subagent#task-management#code-review#prompt-engineering#parallel-execution
One-click install
npx skills add https://github.com/Xza85hrf/claude-code-agent-kit --skill subagent-driven-development-xza85hrf
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/Xza85hrf/claude-code-agent-kit/tree/main/.claude/skills/architecture/subagent-driven-development
Command: npx skills add https://github.com/Xza85hrf/claude-code-agent-kit --skill subagent-driven-development-xza85hrf

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Dispatching fresh, independent subagents per task to enable parallel work with two-stage review, reducing bottlenecks and improving quality in complex plans.

Core Features & Use Cases

  • Fresh subagent per task to ensure isolation and fresh context
  • Two-stage review: spec compliance then code quality
  • TodoWrite style task tracking across tasks
  • Parallel execution of independent tasks within a single plan
  • Clear handoffs between implementer, spec reviewer, and code quality reviewer
  • Works with plan files and per-task prompts

Quick Start

Initialize a plan, dispatch per-task subagents, and begin parallel execution with two-stage reviews for each 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 execute independent tasks in parallel within a single development plan?▼

The approach reduces bottlenecks and improves quality by dispatching fresh, independent subagents per task to enable parallel work with strict two-stage review gates. It ensures isolated contexts for high-quality outcomes in complex plans.

What is two-stage code review in subagent orchestration?▼

Two-stage review in subagent orchestration checks spec compliance first, then evaluates code quality. It enforces strict review gates across tasks through clear handoffs between implementer, spec reviewer, and code quality reviewer prompts.

How do I track progress when running parallel subagent tasks?▼

You track progress by creating TodoWrite artifacts. This provides TodoWrite style task tracking across tasks to monitor the execution status of independent subagents within a single plan.

Does subagent orchestration work with existing plan files and prompts?▼

Yes, subagent orchestration works with plan files and per-task prompts by extracting the plan and dispatching subagents accordingly. It supports implementer, spec reviewer, and code quality reviewer prompts for structured execution.

When should I use fresh subagents for task execution instead of a single agent?▼

You should use fresh subagents for task execution when dealing with plans containing many independent tasks requiring parallel execution and strict review gates. Fresh subagents ensure isolation and fresh context for each individual task.

Related Skills

Explore More Software Engineering Skills→
seankao31seankao31

subagent-driven-development

Dispatch isolated subagents to implement plan tasks with per-task reviews.

Community
Advanced
haojing8312haojing8312
154

workclaw-cleanup-execution

Execute reviewed repository hygiene cleanup batches and route verification through workclaw-change-verification.

Community
Intermediate
TheFJKTheFJK
2

orchestrator

Orchestrate a 5-phase workflow with parallel subagent management.

Community
Advanced
luicabref97luicabref97

sadd:subagent-driven-development

Dispatch fresh subagents for isolated implementation tasks with code-review checkpoints.

Community
Advanced