Borrowing it
Nothing to install: this file belongs to kwakseongjae/oh-my-design. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kwakseongjae/oh-my-design/main/.claude/skills/omd-restraint/SKILL.mdgit clone --depth 1 https://github.com/kwakseongjae/oh-my-designWrote 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.
[](https://agentmods.dev/skills/kwakseongjae/oh-my-design/omd-restraint)<a href="https://agentmods.dev/skills/kwakseongjae/oh-my-design/omd-restraint"><img src="https://agentmods.dev/badge/skills/kwakseongjae/oh-my-design/omd-restraint/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kwakseongjae/oh-my-design/omd-restraint"><img src="https://agentmods.dev/badge/skills/kwakseongjae/oh-my-design/omd-restraint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00324 | $0.05081 |
| Opus 5.5 | $0.00130 | $0.02032 |
| Sonnet 5.5 | $0.00065 | $0.01016 |
| Haiku 4.5 | $0.00032 | $0.00508 |
Grade A, and why
omd:restraint 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
omd-restraint — 덜어내기, 측정해서
절제는 취향이 아니라 양(quantity)과 위계(hierarchy)의 예산이다. 이 스킬은 "덜어내 줘"를 숫자로 바꾼다: 한 화면에 무엇이 몇 개 있는지, 무엇이 지배하는지, 빈 곳이 덩어리인지 부스러기인지를 렌더에서 재고, 넘친 것을 잘라 그 자리를 남은 하나에 준다.
그리고 반대편 실패도 같은 무게로 잰다. 잘라서 얇아진 페이지도 실패다. 장식만 빠지고 아무것도 커지지 않은 화면은 블라인드 심사에서 장식 많은 페이지에 진다(tasteskill의 시험 결과). 그래서 모든 삭제는 "그 자리에 무엇이 커지는가"를 함께 적는다. 적을 수 없으면 자르지 않는다.
근거: docs/research/2026-10-14-restraint/RESTRAINT.md(측정·규칙 R1–R15·cut/keep/enlarge 표),
docs/design-excellence/scale-and-simplicity.md(LC-52/54/55/59, LI-36/37/40), tasteskill v2(MIT, Leonxlnx/taste-skill)의
공개 원칙을 의역해 배웠다. 문장을 옮기지 않았다.
언제 쓰나 / 쓰지 않나
쓴다
- AUDIT — "이 페이지 너무 복잡해", "절제미 점검", "is this too busy?" → 렌더를 재서 규칙표 리포트.
- APPLY — "덜어내 줘", "여백 살려서 다시", "simplify the hero" → 아래 덜어내기 절차로 고치고 재측정.
- 랜딩·제품 소개·카탈로그·문서 첫 화면처럼 방문자가 처음 보는 화면의 양과 위계.
쓰지 않는다
- 브랜드 값(색·서체·radius·간격 토큰) 결정 →
omd-apply/omd-init. 이 스킬은 토큰을 바꾸지 않는다. - 모션 타이밍·타깃 크기·대비 같은 미시 물리 →
omd-feel. - "AI가 만든 것 같다"는 패턴 진단 →
omd-slop-audit. - 밀도를 일부러 올리는 쇼케이스 랜딩(LC-59 밀도 다이얼 ≥ 6) →
omd-landing/omd-aphrodite가 주인. 그때도 R1·R2·R10은 유지한다. - 대시보드·데이터 테이블·폼처럼 밀도 자체가 기능인 앱 화면. 여기서 R2·R4·R8 상한은 틀린 질문이다(표의 선·입력 필드 테두리는 R8에서 이미 제외).
- 정본 레퍼런스 본문을 줄이는 일. 아래 "자르지 않는 것" 참조.
우선순위
- DESIGN.md가 이긴다. 브랜드 토큰·컴포넌트 계약·카피 voice는 그대로. 절제는 몇 개를, 얼마나 크게 쓸지만 정한다. 액센트 1개(R7)는 "DESIGN.md의 액센트를 한 곳에만"이지, 다른 액센트를 고르라는 뜻이 아니다.
.omd/preferences.md의 pending 교정이 DESIGN.md보다 먼저다(omd-apply와 같은 규칙).omd-landing과의 경계 — LC-59 밀도 다이얼 ≤ 5(제품·카탈로그·문서·OmD 사이트)면 이 스킬의 상한이 랜딩의 밀도 바닥(LI-24~26)을 이긴다. 다이얼 ≥ 6(쇼케이스)이면 랜딩 바닥이 적용되고, 여기서는 R1·R2·R10만 유지한다.- 자르지 않는 것(AGENTS.md). 정본 레퍼런스 본문, provenance, "폰트 사용 불가" 표기, JSON-LD, answer-first 요약,
item page의
#use블록(Copy·Download·raw DESIGN.md·설치 명령·첫 프롬프트). 이것들은 keep 또는 demote(작게·뒤로)만 가능하다. 잘리는 것은 크롬(장식·반복·중복)뿐이다.
출처 등급 — 숫자가 얼마나 단단한가
omd-feel처럼 모든 임계값에 등급을 단다. 등급이 강제 강도를 정한다.
What ships with it
5 files 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.
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.
- 11d ago First seen · 175 lines · 324 tokens per session scan A eb2475ccc39a
omd:restraint is a skill published in the GitHub repository kwakseongjae/oh-my-design (549 stars, last pushed yesterday), licensed MIT. It adds 324 tokens to every session and 5,081 once invoked, about $0.0013 per session on Opus 5.5. 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 2026-10-15.
Other skills, from other repositories
dembrandt
A TypeScript command-line tool that renders a web page with Playwright and examines its actual styles. It turns colours, typography, spacing, borders, shadows, animation curves, components, and breakpoints into structured design tokens.
extract-design
Extract the full design language from any website URL. Produces 8 output files including AI-optimized markdown, visual HTML preview, Tailwind config, React theme, shadcn/ui theme, Figma variables, W3C design tokens, and CSS variables. Also runs WCAG accessibility scoring. Use when user says 'extract design', 'get…
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
use-design-md
Apply a Korean brand's published DESIGN.md from the ko-design-md catalog (getdesign.kr) — colors, typography, spacing, radius, components, do's & don'ts — to the UI you are building in the CURRENT project. Use this skill whenever the user wants UI built or restyled in the style of a catalogued Korean service — "토스…
brandmd
Extract a website's design system into a DESIGN.md file. Use when starting a new frontend project, rebuilding a site, or when the user wants AI-generated UI to match an existing brand.
montology
A repo's vocabulary as a database, enforced against the code by a tree-sitter scan — in every language it declares (Python, TypeScript/JS, Go, Rust, Swift, Java, Ruby, Elixir, C/C++, and more). Use BEFORE naming anything in code — a class, struct, function, type, module, table, column, endpoint, event, env var, CLI…