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 saajunaid/caddis-plugin --skill warm-editorial-uigit clone --depth 1 https://github.com/saajunaid/caddis-pluginWrote 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/saajunaid/caddis-plugin/warm-editorial-ui)<a href="https://agentmods.dev/skills/saajunaid/caddis-plugin/warm-editorial-ui"><img src="https://agentmods.dev/badge/skills/saajunaid/caddis-plugin/warm-editorial-ui/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/saajunaid/caddis-plugin/warm-editorial-ui"><img src="https://agentmods.dev/badge/skills/saajunaid/caddis-plugin/warm-editorial-ui.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 | $0.00102 | $0.07458 |
| Opus 5.5 | $0.00041 | $0.02983 |
| Sonnet 5.5 | $0.00020 | $0.01492 |
| Haiku 4.5 | $0.00010 | $0.00746 |
Grade C, and why
warm-editorial-ui scanned grade C with 1 finding 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 29d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Plus Jakarta Sans (body) + JetBrains Mono (data). Bahnschrift is Windows system — no CDN needed. --> How it starts
The opening of the file, as written. The whole thing — 733 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Warm Editorial Refinement — Design System
A premium, editorial-grade UI template built for data-rich internal tools. Combines the warmth of analogue design with the precision of modern SaaS.
Canonical reference apps: scratch/mockups/ceo-dashboard-mockup.html (executive-reviewed baseline)
Design Philosophy
Warm surfaces. Editorial type. Intentional depth. Not corporate grey — warm cream.
This system was designed for XYZ Brand internal tools but is brand-agnostic at the token level. It avoids cold grey SaaS aesthetics and instead uses warm-toned surfaces, editorial typography, and refined component geometry.
Design Tokens
Always define these CSS custom properties in :root:
:root {
/* Brand Accent — replace with your brand color */
--brand: #E10A0A;
--brand-dark: #C00909;
--brand-soft: #FEF2F2;
--brand-tint: rgba(225,10,10,0.08);
/* Warm Surfaces — NOT cold grey */
--bg: #F5F3F0; /* page background */
--surface: #FFFFFF; /* cards, panels */
--surface-2: #F9F8F6; /* subtle inset, inputs */
--surface-3: #F0EDE8; /* deeper inset, table rows */
--surface-hover: #EFEDE9; /* hover states */
/* Warm Borders */
--border: #E5E2DC;
--border-strong: #CCC9C2;
/* Warm Ink (text) — slightly brown-tinged, never cold */
--ink-1: #1A1816; /* primary text */
--ink-2: #3D3A36; /* secondary text */
--ink-3: #6B6760; /* tertiary text */
--ink-4: #9C9890; /* muted/placeholder */
/* Status Palette */
--green: #16A34A;
--green-soft: #F0FDF4;
--green-tint: rgba(22,163,74,0.12);
--green-border: #A7F3D0;
--amber: #D97706;
--amber-soft: #FFFBEB;
--red: #DC2626;
--red-soft: #FEF2F2;
--red-border: #FCA5A5;
--blue: #2563EB;
--blue-soft: #EFF6FF;
--blue-border: #BFDBFE;
/* Radius Scale — generous, not tight */
--r-xs: 4px;
--r-sm: 8px;
--r-md: 12px;
--r-lg: 16px; /* standard cards */
--r-xl: 22px; /* panels, large containers */
/* Shadows — multi-layer, warm-tinted (warm brown base, not cold black) */
--shadow-xs: 0 1px 2px rgba(26,24,22,0.04);
--shadow-sm: 0 1px 3px rgba(26,24,22,0.06), 0 1px 2px rgba(26,24,22,0.04);
--shadow-md: 0 4px 12px rgba(26,24,22,0.08), 0 2px 4px rgba(26,24,22,0.04);
--shadow-lg: 0 10px 30px rgba(26,24,22,0.12), 0 4px 8px rgba(26,24,22,0.06);
/* Typography */
/* NOTE: --font-heading uses Bahnschrift — a Windows 10+ system font.
Falls back to Franklin Gothic Medium on macOS/Linux. Correct for Windows-hosted tools. */
--font-sans: 'Plus Jakarta Sans', system-ui, sans-serif;
--font-heading: 'Bahnschrift', 'Franklin Gothic Medium', 'Arial Narrow', sans-serif;
--font-mono: 'JetBrains Mono', monospace;
}
What ships with it
2 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.
- 29d ago Changed · -72 tokens per session 3be6d7908408
- 1mo ago First seen · 733 lines · 174 tokens per session scan C 790c19018cfe
warm-editorial-ui is a skill published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed 2d ago), licensed MIT. It adds 102 tokens to every session and 7,458 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
render-html-page
Convert a finished trip plan into a polished, self-contained HTML page using the design system.
moai-design-tools
Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…
mcp-host-styling-integration
Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.
anti-slop-frontend
A mechanical, countable anti-slop checklist for AI-generated frontend. Catches the specific signatures an undirected model defaults to: AI-purple glows, Inter-everywhere, em-dashes, div-based fake screenshots, eyebrow-on-every-section, beige+brass "premium" palettes, generic Jane Doe / Acme data. Advisory layer that…
accessibility-a11y
Semantic HTML, keyboard navigation, focus states, ARIA labels, skip links, and WCAG contrast requirements. Use when ensuring accessibility compliance, implementing keyboard navigation, or adding screen reader support.