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-contractgit 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-contract)<a href="https://agentmods.dev/skills/tjdrhs90/rn-launch-harness/rn-harness-contract"><img src="https://agentmods.dev/badge/skills/tjdrhs90/rn-launch-harness/rn-harness-contract/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-contract"><img src="https://agentmods.dev/badge/skills/tjdrhs90/rn-launch-harness/rn-harness-contract.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 | $0.00022 | $0.01144 |
| Opus 5 | $0.00011 | $0.00572 |
| Sonnet 5 | $0.00004 | $0.00229 |
| Haiku 4.5 | $0.00002 | $0.00114 |
Grade A, and why
rn-harness-contract 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.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rn-harness-contract — Phase 4: 계약 협상
Generator와 Evaluator가 빌드 전 완료 기준에 합의한다.
Trigger
오케스트레이터에서 Phase 4로 호출됨.
Input
docs/harness/plans/YYYY-MM-DD-prd.md(PRD)docs/harness/plans/YYYY-MM-DD-design.md(디자인)docs/harness/specs/YYYY-MM-DD-research.md(시장 조사)
Process
Step 1: Generator가 계약안 작성
PRD의 유저 스토리와 디자인 스펙을 기반으로 15~30개의 검증 가능한 기준을 작성:
## Contract Proposal
### 1. 회원가입
- **Test**: 이메일/비밀번호 입력 → 가입 버튼 탭
- **Expected**: 유효성 검사 통과 → 홈 화면 이동 → 유저 데이터 저장
- **Evidence**: typecheck pass + 코드 확인
- **Type**: code
### 2. 로그인 후 홈 피드
- **Test**: 로그인 → 홈 탭 → 데이터 로드
- **Expected**: 로딩 스피너 → 데이터 표시 → 스크롤 가능
- **Evidence**: typecheck pass + 코드 확인
- **Type**: code
### 3. 프로필 수정
- **Test**: 프로필 화면 → 이름 수정 → 저장
- **Expected**: 수정 후 반영, 에러 시 Toast 표시
- **Evidence**: typecheck pass + 코드 확인
- **Type**: code
Step 2: Review (mode-dependent)
Default mode (1-pass):
- Generator writes the contract with mandatory criteria included
- Self-review for completeness and specificity
- Mark as AGREED immediately
- Saves tokens by skipping multi-round negotiation
Strict mode (--strict):
- Evaluator reviews each criterion (specific enough? verifiable? edge cases?)
- Generator revises based on feedback
- Iterate until
## Reviewsection says "AGREED"
필수 기준 (MANDATORY)
모든 계약에 반드시 포함:
Anti-Stub 기준
- AS-1: 핵심 기능이 실제 동작 (setTimeout/mock 아님)
- AS-2: 엔드투엔드 데이터 흐름 (생성 → 저장 → 새로고침 → 존재 확인)
- AS-3: 에러 핸들링 (잘못된 입력 시 적절한 에러 표시)
테스트 기준
- T-1: 테스트 러너 설치 (
npm testexit 0) - T-2: 핵심 비즈니스 로직 유닛 테스트 존재
코드 품질 기준
- CQ-1:
npm run typecheck에러 0개 - CQ-2:
npm run lint에러 0개 - CQ-3:
any타입 사용 0개
FSD 아키텍처 기준
- FSD-1: 레이어 계층 준수 (app → widgets → features → entities → shared)
- FSD-2: 동일 레이어 간 직접 참조 없음
- FSD-3: barrel export (index.ts) 완전성
모바일 UX 기준
- UX-1: 모든 화면 SafeAreaView 사용
- UX-2: 로딩/에러/빈 상태 처리
- UX-3: 터치 타겟 44x44 이상
- UX-4: NativeWind className만 사용 (inline style 금지)
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.
- 10d ago First seen · 160 lines · 22 tokens per session scan A ea3b12ca24f6
rn-harness-contract is a skill published in the GitHub repository tjdrhs90/rn-launch-harness (9 stars, last pushed 9d ago), licensed MIT. It adds 22 tokens to every session and 1,144 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
11-browser-qa
Run post-review browser QA and produce short named videos for a locked happy path and sourced browser edge cases. Use when the user wants concise reviewer evidence for a web journey. Not for API, CLI, automated tests, diff review, or application fixes.
08-three-amigos
Assesses an Epic or Story through one product, delivery, or quality lens, then reconciles three caller-supplied reports. Use when the user wants to refine one before a backlog change. Not for spawning or writing.
beta-testing
Beta testing strategy for iOS/macOS apps. Covers TestFlight program setup, beta tester recruitment, feedback collection methodology, user interviews, signal-vs-noise interpretation, and go/no-go launch readiness decisions. Use when planning a beta, setting up TestFlight, collecting user feedback, or deciding if ready…
screenshot-automation
Generates an automated App Store screenshot pipeline with UI tests for screenshot capture, device framing, localized caption overlays, and multi-size batch export. Use when user wants automated screenshots, App Store screenshot generation, or a fastlane snapshot replacement.
09-for-sure
Run an iterative agent loop that retries until a runnable success condition passes. Use when the user says "for sure", "keep trying until", or wants guaranteed completion against a success command. Not for one-shot tasks or uncheckable goals.
03-assert
Assert the work behaves by iterating the project's coding assertions until they pass, plus optional architecture and frontend facets. Use to validate an implementation. Not for reviewing or writing tests.