
Subagent Driven Development
- 1 installs
- 404 repo stars
- Updated August 5, 2026
- aiskillstore/marketplace
subagent-driven-development is a Claude skill that executes an implementation plan by dispatching a fresh subagent per task with spec and code-quality reviews between tasks.
About
subagent-driven-development is an orchestration skill for executing an implementation plan by dispatching a fresh subagent for each independent task. Between tasks it runs a spec-compliance review and a code-quality review, looping fixes back to the same implementer until both pass. Developers use it when they have a completed plan of mostly independent tasks to execute in the current session.
- Dispatches a fresh subagent per task from an implementation plan
- Runs spec-compliance and code-quality reviews between tasks
- Provides task-dispatch and review templates with a fix loop
Subagent Driven Development by the numbers
- 1 all-time installs (skills.sh)
- Ranked #14,098 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
subagent-driven-development capabilities & compatibility
- Capabilities
- code review · plan execution · orchestration
- Use cases
- orchestration · code review · planning
What subagent-driven-development says it does
Use when executing implementation plans with independent tasks in the current session. Dispatches fresh subagent for each task with code review between tasks.
author: obra/superpowers
npx skills add https://github.com/aiskillstore/marketplace --skill subagent-driven-developmentAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 1 |
|---|---|
| repo stars | ★ 404 |
| Last updated | August 5, 2026 |
| Repository | aiskillstore/marketplace ↗ |
What it does
Execute an implementation plan by dispatching per-task subagents with review gates between tasks.
Who is it for?
Developers with a completed plan of mostly independent tasks to run in the current session.
Skip if: Work that needs a separate session or has heavily interdependent tasks.
When should I use this skill?
When executing implementation plans with independent tasks in the current session.
What you get
Each task is implemented by a fresh subagent and passes spec-compliance and code-quality review before the next task starts.
- Each task implemented, reviewed, and marked complete
- Final integrated review
Files
Subagent-Driven Development
구현 계획을 서브에이전트를 통해 실행하는 오케스트레이션 스킬입니다.
When to Use
다음 조건을 모두 만족할 때:
✅ 완성된 구현 계획이 있음
✅ 대부분 독립적인 태스크들
✅ 현재 세션에서 진행해야 함그렇지 않으면:
- 수동 실행
- 또는 parallel-session "executing-plans" 사용
Execution Loop
각 태스크에 대해:
1. Implementer 서브에이전트 디스패치
- 전체 태스크 텍스트와 컨텍스트 제공
2. 명확화 질문 답변
- 구현 시작 전 모든 질문에 답변
3. Implementer 실행
- 테스팅, 커밋, 셀프 리뷰
4. Spec Compliance Review
- 원래 요구사항 대비 검증
5. Code Quality Review
- 구현 표준 승인
6. 문제 발견 시 수정 루프
- 같은 implementer가 수정하고 재제출
7. 완료 마킹 → 다음 태스크Review Flow
┌─────────────────┐
│ Implementer │
│ (서브에이전트) │
└────────┬────────┘
│
▼
┌─────────────────┐
│ Spec Compliance │◄──┐
│ Review │ │ 실패 시
└────────┬────────┘ │ 수정 요청
│ │
통과 ▼ │
┌─────────────────┐ │
│ Code Quality │───┘
│ Review │
└────────┬────────┘
│
통과 ▼
┌─────────────────┐
│ Complete │
└─────────────────┘Red Flags
❌ 리뷰 단계 건너뛰기
❌ 미수정 이슈가 있는데 진행
❌ Spec 리뷰 전에 Code Quality 리뷰 시작
❌ 서브에이전트 질문에 불완전한 답변Task Dispatch Template
## Task
[태스크 설명]
## Context
- 관련 파일: [파일 목록]
- 의존성: [선행 태스크]
- 제약: [제약 조건]
## Acceptance Criteria
- [ ] [기준 1]
- [ ] [기준 2]
## Test Requirements
- 필요한 테스트 케이스Review Templates
Spec Compliance Review
## Requirement Checklist
- [ ] 기능 요구사항 충족
- [ ] 엣지 케이스 처리
- [ ] 에러 핸들링
- [ ] 성능 요구사항
## Verdict
✅ PASS / ❌ NEEDS_REVISION
## Issues (있을 경우)
- [이슈 설명]Code Quality Review
## Quality Checklist
- [ ] 코드 스타일 준수
- [ ] 테스트 커버리지
- [ ] 명명 규칙
- [ ] 문서화
## Verdict
✅ PASS / ❌ NEEDS_REVISION
## Suggestions
- [개선 제안]Final Review
모든 태스크 완료 후:
1. 전체 변경사항 리뷰
2. 통합 테스트 실행
3. 문서 업데이트 확인
4. 머지 준비 완료 확인Related skills
FAQ
When should subagent-driven-development be used?
When you have a completed implementation plan, the tasks are mostly independent, and the work must proceed in the current session.
What reviews run between tasks?
A Spec Compliance Review checks requirements, then a Code Quality Review approves implementation standards before marking a task complete.