skills.rest
Ab0umar
Ab0umarCOMMUNITY
Explore all skills by this author →
GitHub

subagent-driven-development

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

Updated May 4, 2026
Search Tags:#automation#workflow#planning#development#review#subagent#code-review
One-click install
npx skills add https://github.com/Ab0umar/SRV100_Acc --skill subagent-driven-development-ab0umar
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/Ab0umar/SRV100_Acc/tree/main/.codex/plugins/cache/openai-curated/superpowers/dc902811/skills/subagent-driven-development
Command: npx skills add https://github.com/Ab0umar/SRV100_Acc --skill subagent-driven-development-ab0umar

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Subagent-Driven Development orchestrates plan execution by dispatching fresh subagents per task to avoid context bleed and accelerate iteration.

Core Features & Use Cases

  • Fresh subagent per task to maintain isolated context and enable deterministic per-task work
  • Two-stage review workflow: spec compliance first, then code quality review
  • supports continuous execution with clear escalation for blockers or ambiguity

Quick Start

Start by dispatching an implementer subagent for the first task from your plan and let it complete the task, followed by the spec and code-quality reviews before moving to the next 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 prevent context bleed when executing multiple development tasks in a single workflow?▼

To prevent context bleed during development, dispatch a fresh subagent for each task to maintain isolated context. This approach ensures deterministic per-task work and accelerates iteration by keeping task execution environments completely separate.

What is the best way to automate code review for spec compliance during end-to-end development?▼

Automating code review for spec compliance requires a two-stage review workflow: evaluate spec compliance first, then assess code quality. Apply this structured workflow after each implementation task completes to enforce deterministic reviews.

How do I handle blockers or ambiguity when orchestrating plan execution with subagents?▼

Handling blockers during plan execution requires controlled escalation. When uncertainties arise during subagent-driven development, the workflow enforces clear escalation paths to resolve ambiguity before proceeding to the next independent task.

Can I use subagent-driven development for tasks that are only partly independent?▼

Yes, subagent-driven development supports end-to-end plans where tasks are partly independent. It orchestrates execution by dispatching isolated subagents per task, followed by deterministic spec and code-quality reviews to ensure reliable iteration.

Why does dispatching fresh subagents per task accelerate development iteration?▼

Dispatching fresh subagents per task accelerates iteration by avoiding context bleed between tasks. Each subagent maintains isolated context, ensuring deterministic execution and preventing previous task states from corrupting subsequent work.

Related Skills

Explore More Software Engineering Skills→
Liuchun-ossLiuchun-oss
15

subagent-driven-development

Dispatch independent subagents for isolated task execution and two-stage review.

Community
Advanced
cookeyholdercookeyholder

executing-plans

Executes a written plan with review checkpoints and stepwise verification.

Community
Advanced
dennislee928dennislee928
54

subagent-driven-development

Execute implementation plans by dispatching subagents and reviewing spec compliance and code quality.

Community
Advanced
sheer-reysheer-rey

subagent-driven-development

Coordinate sequential development tasks through fresh subagents with two-stage reviews.

Community
Advanced