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 agentmods add rules/dallionking/ui-validation-kit/ui-validationgit clone --depth 1 https://github.com/Dallionking/ui-validation-kitWhat 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 | $0.00000 | $0.01255 |
| Opus 5 | $0.00000 | $0.00628 |
| Sonnet 5 | $0.00000 | $0.00251 |
| Haiku 4.5 | $0.00000 | $0.00126 |
Grade C, and why
ui-validation scanned grade C with 2 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 yesterday.
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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- **Cross-platform declarative flows:** [Maestro](https://maestro.dev) + Maestro Viewer (CLI 2.6.0+ — live device inside the agent). Install: `curl -Ls 'https://get.maestro.mobile.dev' | bash`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Cross-platform declarative flows:** [Maestro](https://maestro.dev) + Maestro Viewer (CLI 2.6.0+ — live device inside the agent). Install: `curl -Ls 'https://get.maestro.mobile.dev' | bash`. How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Validation Rule
You are validating a UI by driving it like a real user.
Core rules
-
Click-through only. Start at the app's root state. Tap/click visible elements to navigate. Never type URL paths after launch.
-
Fix-before-moving-on, cost-tiered. Cheap fixes (single file, CSS/JSX, missing handler): fix in-flight, max 3 attempts, 90s wall-clock per attempt. Expensive fixes (native rebuild >30s, cross-file, build config): escalate to findings, do not fix.
-
Record everything. Screenshot every state change. Save to
recordings/{platform}-{timestamp}/. Video record where the platform supports it. -
Evidence-based reporting. Every PASS/FAIL cites a screenshot path. No naked verdicts.
Platform detection
| File present | Platform |
|---|---|
Package.swift / *.xcodeproj |
iOS native |
build.gradle / build.gradle.kts |
Android native |
app.json with "expo" |
Expo |
package.json with react-native |
React Native |
package.json with next/vite/astro/remix/svelte/solid |
Web |
Tools by platform
- Mobile / TV / desktop (PRIMARY):
agent-device— one CLI for iOS Simulator, Android Emulator, physical devices, tvOS, Android TV, macOS, Linux.@eNaccessibility refs, screenshots, video, logs, network, replay scripts (.ad), React Native introspection. Install:npm install -g agent-device@latest. - Web (PRIMARY):
agent-browser—@eNrefs, Web Vitals, React DevTools, video recording. Install:npm install -g agent-browser. - Cross-platform declarative flows: Maestro + Maestro Viewer (CLI 2.6.0+ — live device inside the agent). Install:
curl -Ls 'https://get.maestro.mobile.dev' | bash. - iOS raw control:
xcrun simctl(built-in with Xcode) — status_bar override, push, pre-grant permissions - Android raw control:
adb(Android Platform Tools) — logcat, install, screenrecord - Web cross-browser fallback: Playwright MCP (Firefox / WebKit), Chrome DevTools MCP (perf)
- Mobile fallback MCPs (only if
agent-deviceunavailable):ios-simulator-mcp,mobile-mcp,XcodeBuildMCP
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.
- yesterday First seen · 113 lines · 0 tokens per session scan C bbd48976fb17
ui-validation is a cursor rule published in the GitHub repository Dallionking/ui-validation-kit (3 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,255 tokens. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
cursorrules
Kortix is a React Native + Expo app built with TypeScript, NativeWind (Tailwind CSS), and a custom design system.
git-commit-attribution
Git commits must use the human developer identity only; never Cursor Agent co-authorship.
android-viewmodel
Android ViewModel conventions — StateFlow, repository abstraction, coroutines, no LiveData.
project-structure
Cursor rule "project-structure" from HeeGyeong/ComposeSample, covering project structure guide, layer structure, modularization rules, dependency rules and resource management.
cursorrules
ROLE: Android Development Expert EXPERIENCELEVEL: Advanced (10+ years) SPECIALTIES.
ios-ui-development-focus
UI/UX and SwiftUI best practices - HIG compliance, presentation APIs, layout patterns.