rn-harness-design

rn-harness-design is a skill for Claude Code from tjdrhs90/rn-launch-harness. It costs 24 tokens per session (1,066 once invoked), scanned A, original, MIT.

A design-planning step for a React Native app that defines its colors, fonts, light and dark themes, and reusable interface parts. NativeWind is the styling system used to describe these choices in the app.

In plain words
What is it for?
Use it to choose a visual direction and document color scales, text styles, themes, and component variations for the app’s screens.
Why use it?
It turns a product plan into consistent visual rules instead of leaving each screen to choose its own appearance. It also makes common elements such as buttons and cards easier to specify consistently.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the rn-launch-harness plugin — 17 skills shipped together

Good fit Use it to choose a visual direction and document color scales, text styles, themes, and component variations for the app’s screens.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tjdrhs90/rn-launch-harness/rn-harness-design
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.

Any agent
npx skills add tjdrhs90/rn-launch-harness --skill rn-harness-design
Clone the repo
git clone --depth 1 https://github.com/tjdrhs90/rn-launch-harness

Made for: Claude Code.

Or install rn-launch-harness, the plugin that ships this one along with the rest of its 17 skills.

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 rn-harness-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/tjdrhs90/rn-launch-harness/rn-harness-design/github.svg)](https://agentmods.dev/skills/tjdrhs90/rn-launch-harness/rn-harness-design)
Your own site
<a href="https://agentmods.dev/skills/tjdrhs90/rn-launch-harness/rn-harness-design"><img src="https://agentmods.dev/badge/skills/tjdrhs90/rn-launch-harness/rn-harness-design/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.

agentmods 80×15 button for rn-harness-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/tjdrhs90/rn-launch-harness/rn-harness-design"><img src="https://agentmods.dev/badge/skills/tjdrhs90/rn-launch-harness/rn-harness-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,066 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00024 $0.01066
Opus 5 $0.00012 $0.00533
Sonnet 5 $0.00005 $0.00213
Haiku 4.5 $0.00002 $0.00107

Measured 10d ago against content hash 9384bdd04f92, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

rn-harness-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 10d 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/rn-harness-design/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

rn-harness-design — Phase 3: 디자인 시스템

PRD를 기반으로 NativeWind 디자인 시스템을 설계한다.

Trigger

오케스트레이터에서 Phase 3으로 호출됨.

Input

  • docs/harness/plans/YYYY-MM-DD-prd.md (PRD)
  • docs/harness/references/ (있으면)

Process

Step 1: 브랜드 톤 결정

3가지 비주얼 방향 제안:

  1. 미니멀 — 깔끔, 여백, 모노톤
  2. — 따뜻한 색감, 라운드, 친근
  3. 볼드 — 강렬한 색상, 대비, 임팩트

AskUserQuestion으로 사용자 선택.

Step 2: 컬러 시스템

// tailwind.config.js colors 확장
colors: {
  primary: {
    50: '#...',
    100: '#...',
    // ... 900
    DEFAULT: '#...',
  },
  secondary: { ... },
  // Semantic colors
  success: '#...',
  warning: '#...',
  error: '#...',
  info: '#...',
  // Background
  background: '#...',
  surface: '#...',
  // Text
  text: {
    primary: '#...',
    secondary: '#...',
    disabled: '#...',
  },
}

Light/Dark 모드 모두 정의.

Step 3: 타이포그래피

Heading 1: 28px / Bold / line-height 36
Heading 2: 24px / Semibold / line-height 32
Heading 3: 20px / Semibold / line-height 28
Body:      16px / Regular / line-height 24
Caption:   12px / Regular / line-height 16
Label:     14px / Medium / line-height 20

Step 4: 컴포넌트 스펙

주요 컴포넌트 variant 정의:

  • Button: primary, secondary, outline, ghost / sm, md, lg
  • Card: default, elevated, outlined
  • Input: default, error, disabled / with icon
  • Typography: h1, h2, h3, body, caption, label
  • Badge: default, success, warning, error
  • Toast: success, error, info, warning

Step 5: 화면 레이아웃

각 주요 화면의 레이아웃 구조:

<SafeAreaView className="flex-1 bg-background">
  <Header />
  <ScrollView className="flex-1 px-4">
    {/* Content */}
  </ScrollView>
  {/* AdBanner는 SafeAreaView 안, 하단 */}
  <AdBanner />
</SafeAreaView>

Step 6: 광고 배치 디자인

AdMob 광고의 시각적 통합:

  • 배너: 콘텐츠와 자연스럽게 어우러지는 배치
  • 전면: 닫기 버튼 접근성 확보
  • 리워드: 보상 안내 UI 디자인

Step 7: 4축 자체 평가

비중 목표 설명
Design Quality 30% 7/10+ 일관성, 정체성
Originality 25% 6/10+ 커스텀 결정, 템플릿 탈피
Craft 25% 7/10+ 간격, 타이포, 대비
Functionality 20% 8/10+ 사용성

Read the full file on GitHub · 164 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. 10d ago First seen · 164 lines · 24 tokens per session scan A 9384bdd04f92

Subscribe to this mod's changes

rn-harness-design is a skill published in the GitHub repository tjdrhs90/rn-launch-harness (9 stars, last pushed 9d ago), licensed MIT. It adds 24 tokens to every session and 1,066 once invoked, about $0.0001 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.