Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tjdrhs90/rn-launch-harnessnpx agentmods add skills/tjdrhs90/rn-launch-harness/rn-harness-submitWrote 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-submit)<a href="https://agentmods.dev/skills/tjdrhs90/rn-launch-harness/rn-harness-submit"><img src="https://agentmods.dev/badge/skills/tjdrhs90/rn-launch-harness/rn-harness-submit/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-submit"><img src="https://agentmods.dev/badge/skills/tjdrhs90/rn-launch-harness/rn-harness-submit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 29 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 37 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium MCP Rug Pull · line 36 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00035 | $0.04185 |
| Opus 5 | $0.00017 | $0.02093 |
| Sonnet 5 | $0.00007 | $0.00837 |
| Haiku 4.5 | $0.00003 | $0.00419 |
Grade A, and why
rn-harness-submit 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 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.
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 — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rn-harness-submit — Phase 10: Store Submission
Submit the app to App Store and Google Play. Uses App Store Connect API (iOS) and Google Play Developer API v3 (Android).
Trigger
Called by the orchestrator as Phase 10.
Input
docs/harness/config.md(API keys, developer info)docs/harness/handoff/build-result.md(build URLs)docs/harness/store-assets/(screenshots + metadata).env(credentials)
Part 0: Pre-submission checks — run these before anything else
Every one of these has caused a real rejection. See docs/store-gotchas.md for the full
write-ups. Four checks, all cheap:
1. No placeholder purpose strings in the generated Info.plist.
Reading app.json is not enough — Expo applies a package's config plugin whenever the
package is a dependency, whether or not it is listed in plugins. expo-image-picker and
expo-camera inject NSMicrophoneUsageDescription = "Allow $(PRODUCT_NAME) to access your microphone", which Apple rejects under 5.1.1.
npx expo prebuild -p ios --clean --no-install
plutil -p ios/*/Info.plist | grep -i usagedescription
# any "Allow $(PRODUCT_NAME) to ..." → fix before submitting
Fix — if the app only picks photos, drop the key rather than writing a string for a capability the app does not use:
["expo-image-picker", { "microphonePermission": false }]
["expo-camera", { "microphonePermission": false }]
2. Every declared permission belongs to a feature a user can reach. For each
NS*UsageDescription and each Android permission, name the screen that uses it and the path a
user takes to get there. A permission for an unreachable or not-yet-built feature is a
rejection, and "we will use it later" in the review notes makes it worse.
3. Age rating declarations are complete — especially advertising = Yes for any AdMob
build (step A-3.9). Cannot be verified over the API; check the Connect UI.
4. Android: read the merged manifest, not yours. Dependencies merge in their own permissions, and Play Console will demand a declaration for them.
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 · 482 lines · 35 tokens per session scan A 490f0bd2ed51
rn-harness-submit is a skill published in the GitHub repository tjdrhs90/rn-launch-harness (9 stars, last pushed 8d ago), licensed MIT. It adds 35 tokens to every session and 4,185 once invoked, about $0.0002 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
flame-harness-submit
Phase 10 — upload store text metadata + categories via fastlane, then pause with exact manual steps for the final iOS review submission and Android production promotion.
apple-app-delivery
Upload builds, distribute on TestFlight, manage metadata, submit for Beta/App Review, and release on the App Store using Apple's official CLIs and the App Store Connect API. Default stable delivery to APPSTORE so one build can be tested in TestFlight and later submitted to the App Store; choose TESTFLIGHTINTERNALONLY…
ios-app-store-release
Use when preparing, archiving, uploading, or submitting iOS apps through App Store Connect. Covers xcodebuild archive/export, Fastlane deliver, altool/transporter fallback, TestFlight, review submission, App Privacy, export compliance, release safety, and slash commands such as /ios-release and /ios-grade.
apple-release-ops
The mechanics of shipping Apple apps. Use for ANY code signing error ("no signing certificate", "provisioning profile doesn't include...", "revoked certificate"), provisioning profiles, certificates, entitlements, capabilities, TestFlight (groups, expiry, feedback), App Store Connect, uploading builds, xcodebuild…
managing-app-versions
Manages semantic versioning for mobile apps across iOS and Android platforms. Use when the user says "bump version", "increment build number", "set version to", "release patch/minor/major", or "sync build numbers". Single source of truth is .msd/versions/{app-id}/version.json. Syncs to app.json (Expo), Info.plist…
submitting-app-release
Runs pre-flight validation gates and submits the app to App Store Connect and Google Play Console via EAS CLI. Use when the user says "release", "submit to store", "publish", "deploy app", or "submit for review". Always runs release-checklist.js first — never submits past a failing gate without explicit user…