Borrowing it
Nothing to install: this file belongs to tjdrhs90/rn-launch-harness. 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/tjdrhs90/rn-launch-harness/main/CLAUDE.mdgit 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/instructions/tjdrhs90/rn-launch-harness/claude-md)<a href="https://agentmods.dev/instructions/tjdrhs90/rn-launch-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/tjdrhs90/rn-launch-harness/claude-md.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 | $0.00881 | $0.00881 |
| Opus 5 | $0.00441 | $0.00441 |
| Sonnet 5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
rn-launch-harness CLAUDE.md 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 7d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RN Launch Harness
React Native 모바일 앱을 아이디어부터 스토어 출시까지 자동화하는 Claude Code 플러그인.
Architecture
Anthropic의 Harness Design for Long-Running Apps 원칙 기반:
- Generator-Evaluator 분리: 빌드하는 에이전트와 평가하는 에이전트를 분리
- Agent subprocess per phase: 각 Phase는 독립 에이전트로 실행 (컨텍스트 리셋)
- 파일 기반 핸드오프: 에이전트 간 통신은
docs/harness/파일로 수행 - Hard Threshold: 주관적 판단을 구체적 PASS/FAIL 기준으로 변환
- Contract Negotiation: 빌드 전 Generator↔Evaluator 완료 기준 합의
Pipeline
/rn-harness "앱 아이디어" → Research → Plan → Design → Contract → Build → QA → AdMob → Accept(사용자 승인) → Build → Screenshots → Submit
Key Directories
skills/— 각 Phase의 SKILL.md 정의hooks/— 레이트 리밋 자동 재개 스크립트- 파이프라인 산출물 — 런별 격리: Phase 1~4는 유니크한
.rn-harness/<run-id>/에 스테이징, Phase 5에서 최상위<app-slug>/로 졸업하며docs/harness/를 그 안으로 이동 (같은 폴더에서 여러 런 동시 실행 시 충돌 방지)
Hard Gates
- TypeScript 에러 0개
- ESLint 에러 0개
any타입 사용 0개- 스텁 구현 = FAIL
- 콘솔 에러 = FAIL
- SafeAreaView 미사용 = FAIL
Store Submission
iOS (완전 자동)
- App Store Connect API (JWT 인증)
- Bundle ID 등록 → 앱 생성 → 메타데이터 → 스크린샷 → 빌드 → 연령 등급 → 심사 제출
- 심사 제출은
reviewSubmissions3-call 플로우.appStoreVersionSubmissionsCREATE 는 폐기됨(403) - 메타데이터는
WAITING_FOR_REVIEW·IN_REVIEW까지 수정 가능,READY_FOR_SALE에서 잠김
Android (일부 수동)
- Google Play Developer API (Service Account)
- 수동 필요: 앱 생성, IARC 콘텐츠 등급, 데이터 안전 섹션
- 수동 완료 후 AskUserQuestion으로 재개 → AAB 업로드 → 릴리즈
AdMob (수동 생성 → 자동 통합)
- 광고 단위는 AdMob 콘솔에서 수동 생성 (API 미지원)
- 파이프라인이 필요한 광고 단위 목록을 안내
- 사용자가 Ad Unit ID 입력 → 코드에 자동 삽입
- 연령 등급의
advertising을 반드시 Yes 로 — 배너만 있어도 해당. 누락 시 Apple 자동 분석이 사람 심사 전에 반려한다
제출 전 필수 점검
리젝을 실제로 부른 것들. 자세한 내용은 docs/store-gotchas.md.
- Expo 는 의존성에 있으면 config plugin 을 자동 적용한다 —
plugins배열에 없어도.expo-image-picker/expo-camera의 기본 마이크 문구가 그대로 나가 5.1.1 반려를 부른다.plugins가 아니라 prebuild 로 생성된Info.plist를 봐야 한다 - 도달할 수 없는 기능의 권한은 넣지 않는다
- Android 는 병합된 매니페스트를 본다 — 의존성이 밀어 넣은
FOREGROUND_SERVICE_*등은 Play Console 별도 선언 대상이고, 선언에는 데모 영상이 필수다
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.
- 7d ago First seen · 67 lines · 881 tokens per session scan A 4450769404bc
rn-launch-harness CLAUDE.md is an instructions file published in the GitHub repository tjdrhs90/rn-launch-harness (9 stars, last pushed 6d ago), licensed MIT. It adds 881 tokens to every session, about $0.0044 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 instructions, from other repositories
agent-compass mobile-app.instructions.md
Use when modifying the Expo mobile app in apps/mobile-app, including Expo Router screens, native config, React Query, and Jest tests.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).