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.
npx skills add kimsanguine/hplan --skill design-tokengit clone --depth 1 https://github.com/kimsanguine/hplanWrote 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/kimsanguine/hplan/design-token)<a href="https://agentmods.dev/skills/kimsanguine/hplan/design-token"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/design-token.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.01670 |
| Opus 5 | $0.00023 | $0.00835 |
| Sonnet 5 | $0.00009 | $0.00334 |
| Haiku 4.5 | $0.00005 | $0.00167 |
Grade A, and why
design-token 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 8d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design-token
목적
2-step 디자인 파이프라인: Phase A (레퍼런스 수집 → DESIGN_BRIEF.md 생성) → Phase B (토큰/DESIGN.md 생성).
Parse --step from $ARGUMENTS:
--step brief→ Run Phase A only (design-reference 로직)--step token→ Run Phase B only (기존 design-token 로직)--step allor no flag → Run Phase A then Phase B
Phase A — 레퍼런스 수집 (--step brief)
100개 큐레이션 레퍼런스 기반으로 타겟에 맞는 디자인 방향성을 DESIGN_BRIEF.md로 문서화한다. AI가 디자인을 생성하지 않는다. AI는 레퍼런스 필터링과 패턴 추출을 구조화한다.
게이트 체크 (Phase A 실행 전)
이전 discover 단계 타겟 프로파일을 확인한다. 없으면:
"타겟 프로파일이 없습니다. discover 단계를 먼저 완료하거나 타겟(카테고리/대상/톤)을 직접 입력하시겠습니까? (입력: t)"
실행 흐름 (Phase A)
A1 — 타겟 읽기 discover 단계 결과에서 카테고리·대상·톤을 추출한다. 없으면 사용자에게 직접 입력 요청.
A2 — ASCII 미리보기 출력
레퍼런스 목록을 보여주기 전에 반드시 아래 형식으로 출력:
┌─── design-reference 실행 ────────────────────────┐
│ 타겟: [카테고리] / [대상] / [톤] │
│ │
│ [한국] (번호) 사이트명 — 핵심 특징 │
│ ... │
│ [글로벌] (번호) 사이트명 — 핵심 특징 │
│ ... │
│ │
│ 번호로 5-7개 선택 / 전체 분석 (a) / 직접 입력 (m)│
└──────────────────────────────────────────────────┘
A3 — 레퍼런스 필터링 references/site-list-kr.md와 references/site-list-global.md에서 타겟 카테고리 일치 항목을 우선 추출한다. 카테고리 일치 < 6개이면 유사 카테고리로 보완. 타겟 사용자가 자주 쓰는 다른 카테고리 1-2개 추가 권고 (이유: 사용자의 디자인 기대값은 주로 쓰는 모든 앱에서 형성됨).
A4 — 패턴 추출 선택된 5-7개에서 references/design-wisdom.md 원칙 적용:
- 레이아웃 패턴
- 컬러 방향성 (헥스코드 + WCAG 대비비 포함 필수)
- 타이포그래피 (스케일 비율 + 기본 px 포함 필수)
- 인터랙션 패턴
패턴마다 design-wisdom.md do/don't 원칙(원칙 3) 적용: ❌/✅ 1쌍 포함. 랜딩/전환 페이지는 LIFT 모델(프레임워크 10) 4개 요소도 체크.
A5 — DESIGN_BRIEF.md 생성
아래 구조로 생성. 추상적 표현 금지 — 모든 결론에 수치 또는 레퍼런스 근거.
# DESIGN_BRIEF.md
## 타겟 프로파일
- 카테고리:
- 대상:
- 톤:
## 선택된 레퍼런스
| 사이트 | 카테고리 | 적용할 패턴 | 선택 이유 |
## 추출된 디자인 방향성
### 레이아웃
[설명 + ❌/✅ do/don't 1쌍]
### 컬러
[헥스코드 + WCAG 대비비 + ❌/✅ 1쌍]
### 타이포그래피
[스케일 비율 + 기본 px + ❌/✅ 1쌍]
### 인터랙션
[ms + easing + ❌/✅ 1쌍]
## 디자인 방향성 결론
[2-3줄. 구체적 수치와 레퍼런스 사이트로 뒷받침]
What ships with it
3 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.
- 8d ago First seen · 168 lines · 46 tokens per session scan A 344c1289c9a0
design-token is a skill published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 22d ago), licensed MIT. It adds 46 tokens to every session and 1,670 once invoked, about $0.0002 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.
Other skills, from other repositories
ui-first-principles
A method for deciding which information and actions should appear first in a user interface or information architecture.
creating-figures
Creates publication-quality scientific figures for academic papers. Backend is chosen by host paper extension — .tex papers get TikZ figures, .typ papers get CeTZ figures; the two are never mixed. Use when creating block diagrams, system architectures, flowcharts, or technical illustrations for papers and theses.…
user-testing
A user-research planning aid with a quick concept test and a full usability study. A concept test checks whether people understand and want an idea; a usability study checks whether they can complete tasks with it.
design-critique-template
A structured way to review a screen or mockup against the user problem it is meant to solve, then check common usability rules.
ui-pattern-library
A guide for choosing interface patterns based on the user problem a proposed solution must address. A UI pattern is a familiar way of arranging an interaction, such as inline editing or a contextual banner.
starting-a-design-plan
Use when beginning any design process - orchestrates gathering context, clarifying requirements, brainstorming solutions, and documenting validated designs to create implementation-ready design documents.