ui-validation

A rule for testing an app's interface by using it like a person on iOS, Android, or the web. It requires clicking or tapping through visible screens, recording state changes, and keeping screenshot evidence.

In plain words
What is it for?
Use it to validate buttons, navigation, and end-to-end user flows, with screenshots supporting each pass or failure.
Why use it?
It turns vague interface checks into repeatable, evidence-based tests and identifies broken navigation or controls.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/dallionking/ui-validation-kit/ui-validation
Clone the repo
git clone --depth 1 https://github.com/Dallionking/ui-validation-kit
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,255 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured yesterday against content hash bbd48976fb17, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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`.
adapters/cursor/rules/ui-validation.mdc · 113 lines

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

  1. Click-through only. Start at the app's root state. Tap/click visible elements to navigate. Never type URL paths after launch.

  2. 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.

  3. Record everything. Screenshot every state change. Save to recordings/{platform}-{timestamp}/. Video record where the platform supports it.

  4. 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. @eN accessibility refs, screenshots, video, logs, network, replay scripts (.ad), React Native introspection. Install: npm install -g agent-device@latest.
  • Web (PRIMARY): agent-browser@eN refs, 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-device unavailable): ios-simulator-mcp, mobile-mcp, XcodeBuildMCP

Read the full file on GitHub · 113 lines

Changes

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.

  1. yesterday First seen · 113 lines · 0 tokens per session scan C bbd48976fb17

Subscribe to this mod's changes

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.