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-evaluatorgit 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-evaluator)<a href="https://agentmods.dev/skills/tjdrhs90/rn-launch-harness/rn-harness-evaluator"><img src="https://agentmods.dev/badge/skills/tjdrhs90/rn-launch-harness/rn-harness-evaluator/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-evaluator"><img src="https://agentmods.dev/badge/skills/tjdrhs90/rn-launch-harness/rn-harness-evaluator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 MCP Rug Pull · line 210 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 | $0.00032 | $0.03365 |
| Opus 5 | $0.00016 | $0.01682 |
| Sonnet 5 | $0.00006 | $0.00673 |
| Haiku 4.5 | $0.00003 | $0.00336 |
Grade A, and why
rn-harness-evaluator 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 — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rn-harness-evaluator — Phase 5: 3-Phase Progressive QA
Verifies the Generator's build against contract criteria through a progressive 3-phase evaluation pipeline.
Principle
"Run the code, see the app, then judge." Never PASS based on code review alone. Execute commands, capture screenshots when possible, and verify independently.
Trigger
Called by the orchestrator for Phase 5 (Evaluator). The orchestrator sets the QA phase (5.1, 5.2, or 5.3) and the evaluator profile.
Input
docs/harness/contract.md(completion criteria)docs/harness/handoff/round-N-gen.md(Generator handoff)docs/harness/config.md— readevaluatorfield for profile selectionreferences/evaluation-criteria.md(scoring rubrics)- Actual project source code
Evaluator Profiles
Read the evaluator field from docs/harness/config.md to determine the profile:
| Profile | Behavior | When |
|---|---|---|
default |
Phase 5.1 only (functional check). Covers typecheck, lint, FSD, contract criteria. | Default mode — token efficient |
full |
Full 3-phase QA (5.1 → 5.2 → 5.3) | --strict flag |
strict |
All 3 phases with higher thresholds: Design 8+, ALL 6 Agent Team must PASS with zero warnings | --strict with extra rigor |
Default mode runs Phase 5.1 only. This covers the most critical checks (typecheck 0 errors, lint 0, FSD compliance, contract criteria, stubs) at a fraction of the token cost. Phase 5.2 and 5.3 are only activated with --strict.
If no evaluator field is found, use default.
Phase 5.1: Functional (Does it WORK?)
The foundation gate. If the code does not compile, lint, pass tests, and meet the contract, nothing else matters.
Step 1: Run Automated Checks
npm run typecheck 2>&1
npm run lint 2>&1
npm test 2>&1
Record every result. Any error = automatic FAIL for that criterion.
Step 2: NativeWind 6-Check Gate (CRITICAL)
Verify all 6 configuration points:
babel.config.js—jsxImportSource+nativewind/babelpluginmetro.config.js—withNativeWindwrappertailwind.config.js—nativewind/preset+ correctcontentpathsglobal.css—@tailwind base/components/utilitiesdirectives- Root
_layout.tsx—import "./global.css"present nativewind-env.d.ts—/// <reference types="nativewind/types" />
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.
- 10d ago First seen · 407 lines · 32 tokens per session scan A 21f76bd5d8bf
rn-harness-evaluator is a skill published in the GitHub repository tjdrhs90/rn-launch-harness (9 stars, last pushed 9d ago), licensed MIT. It adds 32 tokens to every session and 3,365 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
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…
accessibility-audit
Run a structured accessibility audit on an iOS/macOS app — automated XCUITest audits, Accessibility Inspector, manual VoiceOver/Dynamic Type passes, and App Store Accessibility Nutrition Label evaluation. Use before release, when preparing Nutrition Label declarations, or for EU Accessibility Act compliance.
flutter-testing
A testing guide for Flutter mobile apps and NestJS backends used across multiple regions. It covers unit tests, screen tests, end-to-end tests, regional build variants called flavors, and rules for testing payments, tenants, and external services with test doubles.
ios-screenshot-taker
Use when capturing deterministic iOS simulator screenshots for App Store, TestFlight, QA, launch pages, or marketing decks. Covers xcodebuild build, simulator boot/install/launch, seeded demo states, xcrun simctl screenshots, required App Store device classes, public-safe output handling, and slash commands such as…
ios-release-tester
Produce release-grade evidence for an Apple app build. Use when testing Swift/iOS/iPadOS apps in simulators, real devices, Sandbox, or TestFlight; verifying StoreKit, persistence, migrations, exports, accessibility, adaptive UI, privacy manifests, archives, signing, screenshots, or deciding whether a specific build is…
ui-crawler-max
Autonomous UI crawler for iOS simulator apps — rapid, element-precise data collection. Use whenever the user says "crawl my app", "auto-test the UI", "click/tap through every screen", "monkey test", "explore the app and find errors/crashes", "collect screenshots of all screens", "smoke test the whole app", or asks for…