init-design

init-design is a skill for Claude Code, Codex from cubha/claude-workflow-plugins. It costs 137 tokens per session (3,716 once invoked), scanned A, original, MIT.

A Korean-language procedure for extracting an existing project’s design system into DESIGN-TOKENS.md and UX-BRIEF.md files under docs/design. A design system is the documented set of visual and interface rules used across a product.

In plain words
What is it for?
Use it to scan source files, extract and normalize design tokens, create design documentation, preview results with a dry run, or perform the optional deeper cleanup.
Why use it?
It gives projects without design documentation a common reference while preserving the current design instead of replacing it.

Skill for Claude CodeCodex

Part of the init-design plugin — 1 skill 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/cubha/claude-workflow-plugins/init-design
Any agent
npx skills add cubha/claude-workflow-plugins --skill init-design
Clone the repo
git clone --depth 1 https://github.com/cubha/claude-workflow-plugins

Made for: Claude Code, Codex.

Or install init-design, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for init-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/cubha/claude-workflow-plugins/init-design.svg)](https://agentmods.dev/skills/cubha/claude-workflow-plugins/init-design)
Your own site
<a href="https://agentmods.dev/skills/cubha/claude-workflow-plugins/init-design"><img src="https://agentmods.dev/badge/skills/cubha/claude-workflow-plugins/init-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 137 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,716 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 $0.00137 $0.03716
Opus 5 $0.00068 $0.01858
Sonnet 5 $0.00027 $0.00743
Haiku 4.5 $0.00014 $0.00372

Measured 3d ago against content hash 9ab1b6cd7e27, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init-design 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 3d 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.

plugins/init-design/skills/init-design/SKILL.md · 349 lines

How it starts

The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.

INIT-DESIGN — 디자인 시스템 역추출 파이프라인

$ARGUMENTS 에 대해 아래 파이프라인을 실행한다.

SCAN → EXTRACT → NORMALIZE → GENERATE → [DEEP: CLEANUP] → REPORT

존재 이유: 이미 개발된 프로젝트에서 기존 코드를 Ground Truth로 확정하고 docs/design/ 기준 파일을 역추출로 생성하는 전용 스킬이다. 디자인 토큰이 코드 곳곳에 흩어져 있어 문서화된 단일 기준이 없는 프로젝트에서, 이후 UI 작업의 최우선 참조 기준을 수립한다.

리디자인과의 경계

이 스킬은 기존 디자인을 문서화할 뿐, 교체하지 않는다.

디자인 교체(리디자인) /init-design
목적 디자인 교체 현재 디자인 문서화
코드 변경 스타일 전면 교체 기본 없음 (--deep 시 한정적)
기준 타겟 새 디자인 기존 코드 그대로
출력 새 DESIGN-TOKENS.md 역추출 DESIGN-TOKENS.md

Phase 0: PARSE — 인자 파싱

인자 기본값 설명
대상 경로 src/ 스캔할 소스 루트
--deep OFF 하드코딩 교체 + 유틸 클래스 추출 + 컴포넌트 정리
--dry-run OFF GENERATE 직전까지만 — 토큰 미리보기 출력, 파일 생성 없음
--skip-ux-brief OFF UX-BRIEF.md 생성 생략

Phase 1: SCAN — 현재 디자인 자산 스캔

1-1. 사전 확인

docs/design/ 존재 여부를 Glob으로 확인한다:

상황 동작
docs/design/DESIGN-TOKENS.md 없음 정상 진행
docs/design/DESIGN-TOKENS.md 존재 사용자에게 경고: "이미 파일이 존재합니다. 덮어쓰면 기존 파일은 archive로 이동됩니다. 계속할까요?" → 승인 시 계속, 거절 시 종료

1-2. 디자인 자산 병렬 수집

아래를 병렬로 Read·Glob한다:

수집 대상 경로 패턴 추출 내용
CSS 전역 파일 **/globals.css, **/index.css, **/*.module.css CSS 커스텀 프로퍼티 (:root, [data-theme])
Tailwind 설정 tailwind.config.* theme.extend.* 값 전체
레이아웃 컴포넌트 **/layout/**, **/Header.*, **/Footer.*, **/Sidebar.* 레이아웃 구조·영역 분류
페이지 파일 **/page.tsx, **/page.jsx, **/page.vue 라우트 목록 (화면 맵용)
프로젝트 문서 프로젝트 루트 (CLAUDE.md, README.md, package.json) 기술 스택, 구조 원칙

1-3. 인벤토리 요약 출력

📋 스캔 결과
CSS 변수:    {N}개 (`:root` / `[data-theme]`)
Tailwind 확장: {M}개
커스텀 유틸 클래스: {K}개 (globals.css)
인라인 스타일 하드코딩: {W}개 (대략)
페이지(라우트): {P}개

Phase 2: EXTRACT — 토큰 추출

스캔 결과에서 아래 6개 카테고리로 토큰을 추출한다.

2-1. 추출 소스 우선순위

우선순위 소스 신뢰도
1 CSS :root / [data-theme] 커스텀 프로퍼티 높음 — 이미 토큰화된 값
2 Tailwind theme.extend.* 높음 — 구조적 확장
3 globals.css 커스텀 유틸 클래스 (.btn, .sv-label 등) 중간 — 프로젝트 전용 클래스
4 컴포넌트 className 반복 패턴 중간 — 암묵적 토큰
5 style={{...}} 인라인 하드코딩 낮음 — 정규화 필요

Read the full file on GitHub · 349 lines

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. 3d ago First seen · 349 lines · 137 tokens per session scan A 9ab1b6cd7e27

Subscribe to this mod's changes

init-design is a skill published in the GitHub repository cubha/claude-workflow-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 137 tokens to every session and 3,716 once invoked, about $0.0007 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

repomix

Pack and analyze codebases into AI-friendly single files using Repomix. Use when the user wants to explore repositories, analyze code structure, find patterns, check token counts, or prepare codebase context for AI analysis. Supports both local directories and remote GitHub repositories.

yamadashy/repomix · 58 tokens

amazon-reviews-api-skill

This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…

browser-act/skills · 124 tokens

amazon-competitor-analyzer

Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.

browser-act/skills · 48 tokens

muapi-media-editing

Edit and enhance images and videos with AI via muapi.ai — prompt-based editing, upscaling, background removal, face swap, lipsync, video effects, and more.

SamurAIGPT/Generative-Media-Skills · 41 tokens

ctf-malware

Provides malware analysis and network traffic techniques for CTF challenges. Use when analyzing obfuscated scripts, malicious packages, custom crypto protocols, C2 traffic, PE/.NET binaries, RC4/AES encrypted communications, YARA rules, shellcode analysis, memory forensics for malware (Volatility malfind, process…

ljagiello/ctf-skills · 101 tokens

research

Conduct preliminary research on a topic and generate research outline. For academic research, benchmark research, technology selection, etc.

Weizhena/Deep-Research-skills · 25 tokens