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-harnessgit 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)<a href="https://agentmods.dev/skills/tjdrhs90/rn-launch-harness/rn-harness"><img src="https://agentmods.dev/badge/skills/tjdrhs90/rn-launch-harness/rn-harness/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"><img src="https://agentmods.dev/badge/skills/tjdrhs90/rn-launch-harness/rn-harness.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00031 | $0.03508 |
| Opus 5 | $0.00015 | $0.01754 |
| Sonnet 5 | $0.00006 | $0.00702 |
| Haiku 4.5 | $0.00003 | $0.00351 |
Grade C, and why
rn-harness scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ".rn-harness/$RUN_ID" # remove now-empty staging How it starts
The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/rn-harness — RN Launch Harness
React Native 모바일 앱을 아이디어부터 스토어 출시까지 자동화하는 메인 오케스트레이터.
Arguments
"앱 설명"— 새 파이프라인 시작 (아이디어가 있을 때)- (인자 없음) — 아이디어 발굴부터 시작 (스토어 탑차트 조사 → 1인개발 가능한 앱 추천)
--resume— Resume paused pipeline--status— Check progress--rounds <N>— Max QA rounds per phase (default: 3)--ref <url-or-image>— Reference material (repeatable)--skip-research— Skip market research--skip-admob— Skip AdMob integration--skip-acceptance— Skip the Phase 7.5 human acceptance gate (unattended/CI — logs a loud warning)--strict— Enable full 3-phase QA + Agent Team (costs more tokens)--with-spec— Enable Phase 2.5 spec planning with task checklists
Execution
Step 0: Argument Parsing
if --status → Skill("rn-harness-status")
if --resume → Skill("rn-harness-resume")
Save app description as $APP_IDEA.
Step 1: Bootstrap
Per-run isolation: every pipeline run gets its own unique workspace folder, so multiple runs launched in the same directory never collide on docs/harness/. Nothing is written to a shared root-level docs/.
- Phase 1–4 run inside a unique staging folder
.rn-harness/<run-id>/— in idea-discovery mode the app name isn't known yet, so a timestamp id is used. - Phase 5 (Generator) creates the real Expo project as a top-level
$APP_SLUG/folder and moves the harness artifacts into it. The empty staging folder is then removed.
run-directory/ ← where /rn-harness was invoked (may host MANY runs)
├── .claude/ ← session history
├── .rn-harness/ ← staging container for in-progress runs
│ ├── run-20260709-113045/ ← run A (Phase 1–4) — UNIQUE per invocation
│ │ └── docs/harness/
│ │ ├── config.md · state.md · pipeline-log.md · build-log.md
│ │ ├── specs/ plans/ handoff/ feedback/ references/
│ │ └── screenshots/ store-assets/
│ └── run-20260709-124512/ ← run B — separate folder → NO collision
│ └── docs/harness/
└── budget-book/ ← run A after Phase 5: Expo project (docs moved in)
├── app/ · src/ · scripts/publish.js · credentials/ · .env · .gitignore
└── docs/harness/ ← artifacts now live inside the project
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.
- 9d ago First seen · 311 lines · 31 tokens per session scan C 5d7efa0fb3ee
rn-harness is a skill published in the GitHub repository tjdrhs90/rn-launch-harness (9 stars, last pushed 8d ago), licensed MIT. It adds 31 tokens to every session and 3,508 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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.