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 tjdrhs90/rn-launch-harness --skill rn-harness-researchgit clone --depth 1 https://github.com/tjdrhs90/rn-launch-harnessWrote 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/tjdrhs90/rn-launch-harness/rn-harness-research)<a href="https://agentmods.dev/skills/tjdrhs90/rn-launch-harness/rn-harness-research"><img src="https://agentmods.dev/badge/skills/tjdrhs90/rn-launch-harness/rn-harness-research/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/tjdrhs90/rn-launch-harness/rn-harness-research"><img src="https://agentmods.dev/badge/skills/tjdrhs90/rn-launch-harness/rn-harness-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00023 | $0.01825 |
| Opus 5 | $0.00012 | $0.00912 |
| Sonnet 5 | $0.00005 | $0.00365 |
| Haiku 4.5 | $0.00002 | $0.00183 |
Grade A, and why
rn-harness-research 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rn-harness-research — Phase 1: 시장 조사 & 아이디어 발굴
아이디어가 있으면 시장을 조사하고, 없으면 직접 찾아서 제안한다.
Trigger
오케스트레이터(/rn-harness)에서 Phase 1으로 호출됨.
Input
docs/harness/config.md의app_ideadocs/harness/references/(있으면)
Process
Step 0: 모드 판별
app_idea를 확인:
- 구체적 아이디어 (예: "커피 구독 앱") → Mode A: 시장 조사
- 빈 값 / 모호한 요청 (예: "뭐 만들까", "알아서", "") → Mode B: 아이디어 발굴
Mode A: 시장 조사 (아이디어가 있을 때)
Step 1: 아이디어 분석
app_idea를 읽고 다음을 파악:
- 핵심 도메인 (건강, 금융, 교육, 커머스 등)
- 타겟 사용자층
- 핵심 가치 제안
Step 2: 시장 조사
WebSearch를 사용하여:
- 카테고리 트렌드: 해당 카테고리 App Store/Google Play 인기 앱 조사
- 경쟁 앱 분석: 상위 5~10개 경쟁 앱 분석
- 앱 이름, 평점, 주요 기능, 강점, 약점
- 유저 리뷰에서 반복되는 불만/요청 사항
- 시장 기회: 경쟁 앱이 놓치고 있는 영역
- 수익화 모델: 해당 카테고리에서 흔한 수익 모델 (광고, 구독, 인앱결제)
Step 3: 차별화 전략 수립
경쟁 분석 기반으로:
- 핵심 차별점 3가지
- MVP 핵심 기능 리스트
- "이 앱을 쓰는 이유" 한 줄 정의
Step 4: 기술 타당성 검토
React Native + Expo로 구현 가능한지:
- 필요한 네이티브 모듈 확인
- Expo SDK 지원 여부
- 서드파티 라이브러리 존재 여부
- 백엔드 요구사항 (Firebase, Supabase 등)
→ Step 10: 사용자 확인으로 이동
Mode B: 아이디어 발굴 (아이디어가 없을 때)
Step 5: 스토어 탑 차트 조사
WebSearch로 현재 인기 앱 트렌드 분석:
-
App Store 카테고리별 Top 100 조사
- 생산성, 건강/피트니스, 금융, 교육, 라이프스타일, 유틸리티
- 최근 급상승한 앱, 새로 출시된 앱
- 한국 스토어 + 미국 스토어 동시 조사
-
Google Play 인기 차트 조사
- 무료 인기, 유료 인기, 인기 급상승
- 카테고리별 트렌드
-
최근 트렌드 키워드
- "2026 앱 트렌드", "인기 앱 카테고리"
- ProductHunt, TechCrunch 최신 앱 소식
Step 6: 1인 개발 필터링
발견한 트렌드/아이디어를 다음 기준으로 필터링:
| 기준 | 조건 |
|---|---|
| 1인 개발 가능 | 2주 이내 MVP 구현 가능한 범위 |
| 서버 불필요 | 로컬 저장 (AsyncStorage/SQLite) 또는 Firebase/Supabase 무료 티어 |
| 네이티브 모듈 최소 | Expo SDK로 대부분 커버 가능 |
| 수익화 가능 | AdMob 광고 또는 간단한 인앱결제로 수익 가능 |
| 경쟁 강도 | 대형 기업이 독점하지 않는 틈새 영역 |
| 유지보수 부담 낮음 | 콘텐츠 업데이트/서버 관리 불필요 |
Step 7: 아이디어 후보 생성
3~5개 아이디어를 구체적으로 제안:
### 아이디어 1: [앱 이름]
- **한 줄 소개**: ...
- **타겟**: ...
- **핵심 기능 3가지**:
1. ...
2. ...
3. ...
- **차별점**: 기존 [경쟁앱]은 [약점]이 있는데 이 앱은 [강점]
- **수익화**: AdMob 배너 + 전면 광고 (예상 DAU X명 기준 월 $Y)
- **기술 타당성**: Expo SDK 커버 / 서버 불필요 / 예상 개발 기간 N일
- **시장 근거**: [탑차트 앱]의 리뷰에서 [불만]이 반복됨 → 기회
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.
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 · 233 lines · 23 tokens per session scan A 3f1700986b71
rn-harness-research is a skill published in the GitHub repository tjdrhs90/rn-launch-harness (9 stars, last pushed 9d ago), licensed MIT. It adds 23 tokens to every session and 1,825 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.
Other skills, from other repositories
appstore-publish
A workflow guide for publishing an app to the App Store, including prerequisites, tool loading, submission, and resubmission steps.
playstore-publish
A guide for publishing to Google Play, including required conditions, tool loading, the run sequence, in-app products, and subscriptions. Google Play is Google’s store for Android apps and digital purchases.
app-store-preflight-compliance
Pre-submission compliance scanner workflow for Apple App Store apps. Use when reviewing iOS, macOS, tvOS, watchOS, or visionOS projects (Swift, Objective-C, React Native, Expo) for App Store rejection risks, submission readiness, privacy compliance, or guideline violations.
ios-marketing-capture
Use when the user wants to automate capture of marketing screenshots for a SwiftUI iOS app across multiple locales, devices, or appearances. Covers full-screen shots, isolated element renders (carousel cards, widgets), and reproducible output naming. Triggers on marketing screenshots, locale screenshots, widget…
implementation-guide
Generates detailed implementation guide with pseudo-code and step-by-step development instructions. Creates IMPLEMENTATIONGUIDE.md from PRD, Architecture, and UX specs. Use when creating development roadmap.
architecture-spec
Generates technical architecture specification from PRD. Covers architecture pattern, tech stack, data models, and app structure. Use when creating ARCHITECTURE.md or designing system architecture.