A command for handling an implementation request through planning, coding, review, testing, and quality checks with multiple coordinated work streams.

Coordinating architecture, implementation, security and performance checks, testing, merging, and follow-up work through the listed PDCA steps.

It breaks a large coding task into separate areas of work and brings the results together for final checks.

superwork — Command by demodev-lab

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/demodev-lab/claude-code-plugin-demokit/superwork

Clone the repo

git clone --depth 1 https://github.com/demodev-lab/claude-code-plugin-demokit

Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 896 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00078	$0.00896
Opus 5	$0.00039	$0.00448
Sonnet 5	$0.00016	$0.00179
Haiku 4.5	$0.00008	$0.00090

Measured 2d ago against content hash 6a29b316570a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

superwork scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/superwork.md · 87 lines

What it actually says

/superwork (Team Orchestrator)

/superwork <구현내용>

구현내용 한 건을 최고 성능 팀 협업 모드로 처리한다.

동작 가이드

요건 정리
- 구현 목표, 범위, 성공 조건을 한 번에 정의한다.
- 산출물 경계(파일/모듈/테스트 범위)를 명확히 한다.
- 자동으로 Plan 템플릿이 생성돼 작업 단위를 체크리스트화한다.
병렬 팀 투입
- 아키텍처/설계, 핵심 구현, 보안·성능 점검, 테스트/QA를 가능한 병렬 태스크로 분할해 team 오케스트레이션으로 동시 실행한다.
- /superwork는 입력 내용을 기준으로 병렬 그룹(동시 수행 가능 태스크)을 제안한다.
- /pdca 정석 순서는 /pdca plan → /pdca design → /pdca do → /pdca analyze → /pdca iterate(조건부) → /pdca report → /pdca status//pdca next 입니다.
통합 검증
- 구현 결과를 병합하고 충돌/중복/품질 리스크를 정리한다.
- 테스트, 리뷰, 보안/성능 점검을 끝까지 완료한다.
- /pdca analyze//pdca iterate 연동으로 gap-rate 개선까지 반복 제안한다.
성과 정리
- 최종 요약, 미해결 리스크, 후속 작업을 정리해 다음 명령으로 이어갈 수 있게 한다.
- /pdca report 및 /pdca status//pdca next와 연동해 다음 단계 이동을 점검한다.

실행 템플릿 자동 생성

/superwork 입력 즉시 내부 엔진이 다음을 생성한다.
- 요청 분해 템플릿 (Plan/Design/Do/Analyze/Iterate/Report)
- 병렬 태스크 그룹 제안
- /pdca 연동 커맨드 체인
- /pdca do에 바로 붙여 쓰는 체크리스트 템플릿

/superwork 회원가입 API 구현
/superwork "결제 취소 예외 처리 보강"

`/pdca do` 실행 체크리스트 예시

/pdca do 회원가입-api-구현
- [ ] 1. Entity + Repository 구현 (domain-expert)
- [ ] 2. Service 핵심 로직 구현 (service-expert)
- [ ] 3. DTO/요청-응답 스펙 및 검증 (api-expert)
...

권장 체크리스트

/pdca plan <구현내용>
/pdca design <구현내용>
/pdca do <구현내용>
/pdca analyze <구현내용>
/pdca iterate <구현내용>
/pdca report <구현내용>
/pdca status
/pdca next
/test all
/review
/qa test
/qa log

팀 성능 튜닝 참고(필요 시)

대규모 작업은 team.delegateMode=false 및 충분한 team.maxTeammates 설정을 우선 확인.
병목 구간은 team.performance.phaseMemberCap/team.performance.phaseMaxParallel로 추가 조절.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 87 lines · 78 tokens per session scan A 6a29b316570a

Subscribe to this mod's changes

superwork is a command published in the GitHub repository demodev-lab/claude-code-plugin-demokit (2 stars, last pushed 6mo ago), licensed MIT. It adds 78 tokens to every session and 896 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Planning

superwork

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

/superwork (Team Orchestrator)

동작 가이드

실행 템플릿 자동 생성

`/pdca do` 실행 체크리스트 예시

권장 체크리스트

팀 성능 튜닝 참고(필요 시)

What this file has done since we first saw it

Other commands, from other repositories

claude-flow-swarm

bootstrap

ox-session-review

add-agent

handoff

xdo

superwork

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

/superwork (Team Orchestrator)

동작 가이드

실행 템플릿 자동 생성

/pdca do 실행 체크리스트 예시

권장 체크리스트

팀 성능 튜닝 참고(필요 시)

What this file has done since we first saw it

Other commands, from other repositories

claude-flow-swarm

bootstrap

ox-session-review

add-agent

handoff

xdo

`/pdca do` 실행 체크리스트 예시