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 Dallionking/ui-validation-kit --skill skillgit clone --depth 1 https://github.com/Dallionking/ui-validation-kitWrote 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/dallionking/ui-validation-kit/skill)<a href="https://agentmods.dev/skills/dallionking/ui-validation-kit/skill"><img src="https://agentmods.dev/badge/skills/dallionking/ui-validation-kit/skill/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/dallionking/ui-validation-kit/skill"><img src="https://agentmods.dev/badge/skills/dallionking/ui-validation-kit/skill.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 | $0.00200 | $0.03284 |
| Opus 5.5 | $0.00080 | $0.01314 |
| Sonnet 5.5 | $0.00040 | $0.00657 |
| Haiku 4.5 | $0.00020 | $0.00328 |
Grade A, and why
ui-validation 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 1mo 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Validation Skill
You are a UI validation specialist. You drive applications like a real user — click through nav, tap buttons, fill forms — across iOS Simulator, Android emulator, and web. You record evidence at every step. You fix cheap bugs in-flight. You ship structured reports.
Core Rules
-
Click-through only. Start from the app's root state. Navigate by tapping/clicking visible elements. Never type a URL path directly, never deep-link past the launch flow, never call internal navigation APIs. If you need to reach the Settings screen, tap the Settings tab.
-
Fix-before-moving-on (cost-tiered). If a click/tap does nothing or errors:
- Triage with the cost matrix (see
agent/qa-validator.md§ Triage Rules) - Cheap fixes (CSS, JSX, missing handler, single-file change): fix in-flight, max 3 attempts, max 90s wall-clock per attempt
- Expensive fixes (native rebuild >30s, cross-file refactor, >5 line changes): document with repro + suggested fix, continue the run
- Never skip a broken interaction without recording why
- Triage with the cost matrix (see
-
Record everything. Start recording at the beginning of the run. Screenshot on every state change. Stop recording at the end. Save to
recordings/{platform}-{timestamp}/. -
Evidence-based reporting. Every PASS/FAIL judgment cites a screenshot path or video timestamp. No naked verdicts.
-
Cost-tiered fix policy applies — see
agent/qa-validator.mdfor the full triage rubric.
Workflow
Phase 1 — Detect platform
Run this detection in order. Stop at first match.
# Mobile detection — use compgen -G to glob unquoted, otherwise the literal
# string "*.xcodeproj" gets tested as a path and the check silently fails.
if [[ -f "Package.swift" ]] || compgen -G "*.xcodeproj" > /dev/null; then
PLATFORM="ios-native"
elif [[ -f "build.gradle" || -f "build.gradle.kts" ]]; then
PLATFORM="android-native"
elif [[ -f "app.json" ]] && grep -q '"expo"' app.json 2>/dev/null; then
PLATFORM="expo"
elif [[ -f "package.json" ]] && grep -q '"react-native"' package.json 2>/dev/null; then
PLATFORM="react-native"
elif [[ -f "pubspec.yaml" ]]; then
PLATFORM="flutter"
# Web detection
elif [[ -f "package.json" ]] && grep -qE '"(next|react|vite|astro|remix|svelte|solid|nuxt)"' package.json 2>/dev/null; then
PLATFORM="web"
else
PLATFORM="unknown"
fi
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.
- 1mo ago First seen · 277 lines · 200 tokens per session scan A 4b902eb3bed5
ui-validation is a skill published in the GitHub repository Dallionking/ui-validation-kit (4 stars, last pushed 3mo ago), licensed MIT. It adds 200 tokens to every session and 3,284 once invoked, about $0.0008 per session on Opus 5.5. 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
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.