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 arpitbbhayani/ape-skills --skill ape-design-reviewgit clone --depth 1 https://github.com/arpitbbhayani/ape-skillsWrote 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/arpitbbhayani/ape-skills/ape-design-review)<a href="https://agentmods.dev/skills/arpitbbhayani/ape-skills/ape-design-review"><img src="https://agentmods.dev/badge/skills/arpitbbhayani/ape-skills/ape-design-review/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/arpitbbhayani/ape-skills/ape-design-review"><img src="https://agentmods.dev/badge/skills/arpitbbhayani/ape-skills/ape-design-review.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 | $0.00092 | $0.01080 |
| Opus 5.5 | $0.00037 | $0.00432 |
| Sonnet 5.5 | $0.00018 | $0.00216 |
| Haiku 4.5 | $0.00009 | $0.00108 |
Grade A, and why
array-ui-review 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 4d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Array UI Review (array-ui-review)
Audit technical frontend code and running pages against the Array UI design rules. Do not restyle code while auditing; list every violation with file and line number, state the invariant it violates, and provide a one-line fix.
1. Automated Code Searches
Run these audit commands across src/ (or the project root):
# 1. Custom CSS files (Violates Invariant 1: 0% Custom CSS)
find src/ -name "*.css" ! -name "globals.css" ! -name "styles.css" ! -name "tokens.css" ! -name "shadcn.css"
# 2. Page-level <style> blocks (Violates Invariant 1: 0% Custom CSS)
grep -rnE "<style" src/
# 3. Ad-hoc inline margin/padding hacks (Must use <Gutter> or Layout primitives)
grep -rnE "style=\{\{[^}]*(margin|padding|background|color)" src/
# 4. Heavy drop shadows (Array UI uses flat card surfaces with 1px hairlines)
grep -rnE "shadow-(md|lg|xl|2xl)" src/
# 5. Arbitrary gradients (Gradients are strictly prohibited)
grep -rnE "bg-gradient-to|from-[a-z]+-[0-9]+|to-[a-z]+-[0-9]+" src/
# 6. Bouncy / pill buttons (Buttons must be machined with radius-md / 6px)
grep -rnE "rounded-full|rounded-2xl|rounded-3xl" src/
# 7. Unwrapped action buttons or status indicators (Must be wrapped in <Tooltip>)
# Check for bare <Button>, <ThemeToggle>, or <PingStatus> without a parent <Tooltip>
grep -rnE "<Button|<ThemeToggle|<PingStatus" src/
# 8. Outdated dark crimson (#e60012 must be #ff3344 in dark mode)
grep -rnE "#e60012" src/
2. Visual & Architectural Invariants Checklist
- Font Enforcement:
- Is Google Fonts (
Assistant,IBM Plex Mono,Lora) imported inglobals.cssor<head>? - Does
bodyhavefont-family: var(--font-sans)? - If missing, text defaults to system Inter/Arial, breaking the editorial look.
- Is Google Fonts (
- PageShell Usage:
- Is the page framed inside
<PageShell navbar={<Navbar ... />} footer={<Footer ... />}>? - If a page has custom ad-hoc layout wrappers or manual margins, flag for replacement with
PageShell.
- Is the page framed inside
- Footer Elegance:
- Is the footer rendered on flat canvas (
bg-background) withborder-t border-border? - Are links inline with subtle hints
(hint), without heavy box badges stretching the row? - Are social handles rendered using
<SocialPill>s with tooltips?
- Is the footer rendered on flat canvas (
- Visual Rhythm (Anti-Card-Soup):
- Are there consecutive stacks of identical cards or symmetric blocks?
- Did the page alternate prose with dense telemetry (
Terminal,DiffBlock,ParamTable) and editorial quotes (Maxim)?
- Action Clarity (Tooltip Wrapping):
- Is every action button, icon trigger, theme toggle, and status dot wrapped in
<Tooltip content="...">?
- Is every action button, icon trigger, theme toggle, and status dot wrapped in
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.
- 4d ago First seen · 84 lines · 92 tokens per session scan A 395c90557fd3
array-ui-review is a skill published in the GitHub repository arpitbbhayani/ape-skills (49 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 1,080 once invoked, about $0.0004 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 2026-10-18.
Other skills, from other repositories
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build landing pages, websites, dashboards, web components, or any frontend UI. Generates creative, polished code that avoids generic AI aesthetics.
slop-eval
Objectively evaluate a UI/web design against the pols.dev anti-slop design law: detect catalogued slop tells with cited evidence, score 8 weighted axes (color, type, components, layout, motion, execution, signature, cohesion), and emit a Slop Report with a 0–100 Slop Index and grade. Use when the user asks to…
theming
Use when building a theme or theming system for an interface. Covers token architecture, dark mode, contrast preservation across themes, and generating a coherent palette from a seed colour. Trigger on "add dark mode", "contrast breaks in dark mode", "white-label this app", "generate a palette from our brand color".…
design-systems
Use when building or maintaining a component library and design tokens. Covers token architecture, component API design, variants and states, documentation, and governing adoption across a codebase. Trigger on "build a component library", "we have six different button components", "set up design tokens", "what props…
liquid-glass
Liquid glass — Apple-style frosted, refracting surfaces. Use when the user asks for glassmorphism, frosted/translucent panels, cards, menus or a glass topbar; when a glass surface looks wrong (gray, flat, invisible, unreadable text); or when another skill needs the glass recipe.
color-accessibility
Trigger on: check contrast, WCAG contrast, accessible colors, readable text color, fix low-contrast, dimmed text color, palette accessibility, pastel color, textcolor for background, make this color readable, UI theme contrast, Neovim highlight contrast. Evaluate, fix, and generate accessible fg/bg pairs with the…