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 korbinjoe/TeemAI --skill ui-reviewergit clone --depth 1 https://github.com/korbinjoe/TeemAIWrote 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/korbinjoe/teemai/ui-reviewer)<a href="https://agentmods.dev/skills/korbinjoe/teemai/ui-reviewer"><img src="https://agentmods.dev/badge/skills/korbinjoe/teemai/ui-reviewer/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/korbinjoe/teemai/ui-reviewer"><img src="https://agentmods.dev/badge/skills/korbinjoe/teemai/ui-reviewer.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 | $0.00118 | $0.03213 |
| Opus 5 | $0.00059 | $0.01606 |
| Sonnet 5 | $0.00024 | $0.00643 |
| Haiku 4.5 | $0.00012 | $0.00321 |
Grade A, and why
ui-reviewer 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 — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Process Overview
Code implementation → Layer 0: Code static audit → Fix code issues
→ Browser preview verification
→ Layer 1: Visual defect scan
→ Layer 2: Design aesthetic evaluation
→ Layer 3: AI-generated code typical issues
→ Iterative fixes
→ Multi-viewport verification (required before delivery)
Prerequisites
- Complete Layer 0 code static audit (see below)
- Use
mcp__playwright__browser_navigateto open the page - Use
mcp__playwright__browser_snapshotto get page snapshot - Examine the page with a "find problems" mindset, not "go through the motions"
Knowledge Base Reference
When design judgment basis is needed during review, read the references/ directory:
references/design-heuristics.md— 10 core design heuristics + page layout best practices + component composition patterns + spacing/font-size quick referencereferences/shadcn-design-system.md— Shadcn component mapping + Lucide icon specs + HSL color variables + typography/states/a11y specsreferences/dashboard-design.md— Dashboard information architecture + layout patterns + data visualization selection + metric card design + anti-pattern checklist
Layer 0: Code Static Audit
Execute before browser preview. Scan newly created or modified
.tsx/.tsfiles via Grep/Read to catch code-level issues early.
1. Tailwind Arbitrary Value Detection (Magic Numbers)
Scan: Grep for \-\[\d+px\] or \-\[\d+rem\]
// Not allowed
className="w-[347px] h-[52px] mt-[13px] p-[7px]"
// Correct
className="w-80 h-14 mt-3 p-2"
Exempt: max-w-[...] for container width limits, min-h-[...] for touch targets, grid-cols-[...] for custom grids
2. Responsive Breakpoint Coverage
Scan: Grep for grid-cols-[2-9] or flex.*gap, check for sm: / md: / lg: prefixes
// Not allowed
className="grid grid-cols-4 gap-4"
// Correct
className="grid grid-cols-1 sm:grid-cols-2 lg:grid-cols-4 gap-4"
What ships with it
3 files 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 · 312 lines · 118 tokens per session scan A 94ee5d5c5644
ui-reviewer is a skill published in the GitHub repository korbinjoe/TeemAI (2 stars, last pushed 2mo ago), licensed MIT. It adds 118 tokens to every session and 3,213 once invoked, about $0.0006 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
frontman-dev
AI-powered visual frontend editing in your browser. Click any element in your running app, describe changes in plain English, and get real source file edits with instant hot reload. Works with Next.js, Astro, and Vite.
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
html-artifacts
Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for saveplan, outputiframe, or slackattachhtml.
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
redesign-existing-projects
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.
minimalist-ui
Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.