pdca

A workflow for managing software work through six stages: plan, design, build, analyze, improve, and report. PDCA is a step-by-step improvement cycle, and this version also tracks feature progress.

In plain words
What is it for?
Use it to define requirements, design APIs and database models, build application layers and tests, check implementation gaps, repeat fixes, and create reports.
Why use it?
It gives feature development a repeatable process and makes gaps between the design and the implementation easier to identify.

Skill for Claude CodeCodex

Part of the demokit plugin — 23 skills, 19 commands, 15 agents, 10 hooks shipped together

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 skills/demodev-lab/claude-code-plugin-demokit/pdca
Any agent
npx skills add demodev-lab/claude-code-plugin-demokit --skill pdca
Clone the repo
git clone --depth 1 https://github.com/demodev-lab/claude-code-plugin-demokit

Made for: Claude Code, Codex.

Or install demokit, the plugin that ships this one along with the rest of its 23 skills, 19 commands, 15 agents, 10 hooks.

Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,161 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.

ModelPer sessionOnce invoked
Fable 5 $0.00081 $0.02161
Opus 5 $0.00041 $0.01081
Sonnet 5 $0.00016 $0.00432
Haiku 4.5 $0.00008 $0.00216

Measured 2d ago against content hash 7ed2c4e014f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pdca 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.

skills/pdca/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/pdca - PDCA 워크플로우

help

인자가 help이면 아래 도움말만 출력하고 실행을 중단한다:

/pdca — PDCA 워크플로우 관리

사용법:
  /pdca {subcommand} {feature}

하위 명령:
  plan      요구사항 정의 + API 초안 + 데이터 모델 초안
  design    DB 스키마 상세 + API 상세 + 패키지 구조
  do        Entity → Repo → Service → Controller → DTO → Test 구현
  analyze   설계 vs 구현 Gap 분석
  iterate   Match Rate < 90% 시 자동 수정 반복
  report    완료 보고서 생성
  status    현재 PDCA 상태 조회
  next      다음 단계 안내
  archive   완료된 feature 아카이브
  cleanup   완료된 모든 feature 일괄 아카이브
  force-stop  PDCA 미완료 차단 해제 (강제 종료)

예시:
  /pdca plan user-management
  /pdca design user-management
  /pdca do user-management
  /pdca status
  /pdca next
  /pdca force-stop
  /pdca archive user-management
  /pdca cleanup

관련 명령:
  /crud — CRUD 일괄 생성
  /test — 테스트 코드 생성
  /loop — 자동 반복 실행

하위 명령

/pdca plan {feature}

요구사항 정의 + API 초안 + 데이터 모델 초안

컨벤션: templates/shared/ask-user-convention.md 참조

  1. feature명으로 PDCA 상태 파일 생성 (.pdca/{feature}.status.json)
  2. spring-architect 에이전트 호출
  3. AskUserQuestion 도구로 요구사항 수집 (줄글 질문 금지):
    • Q1 (header: "핵심 기능"): 주요 기능 선택 (multiSelect: true, 도메인에 맞는 선택지 동적 생성)
    • Q2 (header: "사용자 역할"): 역할 선택 (multiSelect: true, 예: 일반 사용자/관리자/게스트)
    • Q3 (header: "외부 연동"): 외부 시스템 연동 여부 (예: 없음/소셜 로그인/결제 PG/알림 서비스)
    • Q4 (header: "인증 방식"): 인증 방식 선택 (예: JWT/Session/OAuth2, 해당 시에만)
  4. Plan 문서 생성 (.pdca/{feature}/plan.md):
    • 요구사항 목록
    • API 엔드포인트 초안 (Method + Path + 설명)
    • Entity 초안 (이름 + 주요 필드)
    • 기술적 고려사항
  5. 상태 업데이트: plan → completed

/pdca design {feature}

DB 스키마 상세 + API 상세 + 패키지 구조

  1. Plan 문서 로드 및 확인
  2. 병렬 설계 — 다음 Task들을 한 메시지에서 동시에 호출:
    • Task 1 (domain-expert): DB 스키마 상세 설계 (테이블, 컬럼, 제약조건, 인덱스)
    • Task 2 (api-expert): API 상세 스펙 (Request/Response Body, 상태 코드)
  3. spring-architect가 결과를 통합하여 Design 문서 생성 (.pdca/{feature}/design.md):
    • DB 테이블 스키마
    • API 상세 스펙
    • Entity 관계도
    • 패키지별 클래스 목록
    • 구현 순서
  4. 상태 업데이트: design → completed

/pdca do {feature}

Entity → Repo → Service → Controller → DTO → Test 구현

Read the full file on GitHub · 206 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 2d ago First seen · 206 lines · 81 tokens per session scan A 7ed2c4e014f3

Subscribe to this mod's changes

pdca is a skill published in the GitHub repository demodev-lab/claude-code-plugin-demokit (2 stars, last pushed 6mo ago), licensed MIT. It adds 81 tokens to every session and 2,161 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens