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 LuuOW/meridian-mcp --skill react-dashboard-cardsgit clone --depth 1 https://github.com/LuuOW/meridian-mcpWrote 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/luuow/meridian-mcp/react-dashboard-cards)<a href="https://agentmods.dev/skills/luuow/meridian-mcp/react-dashboard-cards"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/react-dashboard-cards/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/luuow/meridian-mcp/react-dashboard-cards"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/react-dashboard-cards.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 | $0.00048 | $0.06393 |
| Opus 5 | $0.00024 | $0.03197 |
| Sonnet 5 | $0.00010 | $0.01279 |
| Haiku 4.5 | $0.00005 | $0.00639 |
Grade A, and why
react dashboard cards 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 6d 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 — 679 lines — stays where its author put it; the contents beside it link to each section on GitHub.
React Dashboard Cards Skill Guide
Objective
Build data-rich admin dashboards with consistent, scannable card layouts. Patterns extracted from two production codebases: a B2B lead-gen engine (Vite + shadcn/ui) and a SEO pipeline dashboard (Next.js App Router + custom CSS variables).
1) Design Token Systems
shadcn/ui approach (Tailwind + CSS vars)
:root {
--primary: 221.2 83.2% 53.3%;
--muted-foreground: 215.4 16.3% 46.9%;
--border: 214.3 31.8% 91.4%;
--radius: 0.5rem;
}
Components reference hsl(var(--primary)) etc.
Custom CSS variable approach (seo-geo-aeo pattern)
:root {
--fg: #0f172a;
--muted: #64748b;
--bg: #ffffff;
--bg-elevated: #f8fafc;
--border: rgba(0,0,0,0.08);
--border-strong:rgba(0,0,0,0.14);
--accent: #0d6d8a;
--accent-fg: #ffffff;
--green: #3ecf8e;
--yellow: #eaaf2a;
--red: #f57265;
--blue: #46afc8;
--radius: 10px;
--radius-sm: 6px;
--radius-lg: 16px;
}
.dark { /* override all */ }
Use color-mix(in srgb, var(--accent) 13%, transparent) for tinted backgrounds — no opacity hacks needed.
2) Glass Card Component
// SEO dashboard pattern — custom CSS vars, no shadcn
import clsx from 'clsx'
export function Card({ children, className, style }) {
return (
<section
className={clsx('glass-card rounded-[var(--radius-lg)] p-5', className)}
style={style}
>
{children}
</section>
)
}
/* globals.css */
.glass-card {
background: color-mix(in srgb, var(--bg-elevated) 94%, transparent);
border: 1px solid var(--border);
backdrop-filter: blur(12px);
}
3) StatCard — Icon + Label + Value
shadcn/ui version
function StatCard({
icon: Icon,
label,
value,
variant = 'slate',
}: {
icon: React.ElementType
label: string
value: string | number
variant?: 'slate' | 'red' | 'green'
}) {
const colors = { slate: 'text-slate-600', red: 'text-red-500', green: 'text-green-600' }
return (
<Card>
<CardContent className="pt-4">
<div className="flex items-center gap-3">
<Icon className={cn('h-5 w-5', colors[variant])} />
<div>
<p className="text-xs text-muted-foreground uppercase tracking-wide">{label}</p>
<p className={cn('text-2xl font-semibold tabular-nums', colors[variant])}>{value}</p>
</div>
</div>
</CardContent>
</Card>
)
}
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.
- 6d ago First seen · 679 lines · 48 tokens per session scan A 179e05fe7bca
react dashboard cards is a skill published in the GitHub repository LuuOW/meridian-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 6,393 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
prototype-to-production
Convert design prototypes (HTML, CSS, Figma exports) into production-ready components. Analyzes prototype structure, extracts design tokens, identifies reusable patterns, and generates typed React components. Adapts to existing project tech stack with React + TypeScript as default.
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…
frame-data-rollup
A native Remotion data frame — bars grow from zero by real data via spring physics while the figures roll 0→target in sync. The numbers come alive in a way a static HTML chart can't.
remotion
Create editable AI video projects with Remotion and React, then preview and render them to MP4. Use for vertical short videos, product demos, story-driven animations, HUD/tech visuals, feed ads, tutorial videos, subtitles, voiceover, sound effects, and code-based video iteration.
nerv-ui
Build original, accessible React command-center interfaces with the published @mdrbx/nerv-ui component library. Use for dashboards, monitoring terminals, operational tools, authentication screens, or sharp industrial HUD-style UI in React, Vite, or Next.js.
algolia-search-v2
Algolia Search Integration workflow skill. Use this skill when the user needs Expert patterns for Algolia search implementation, indexing and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.