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 agentmods add skills/xsovad06/sova/dashboard-designnpx skills add xsovad06/sova --skill dashboard-designgit clone --depth 1 https://github.com/xsovad06/sovaWrote 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/xsovad06/sova/dashboard-design)<a href="https://agentmods.dev/skills/xsovad06/sova/dashboard-design"><img src="https://agentmods.dev/badge/skills/xsovad06/sova/dashboard-design.svg" alt="Measured on agentmods" 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 | $0.00066 | $0.02742 |
| Opus 5 | $0.00033 | $0.01371 |
| Sonnet 5 | $0.00013 | $0.00548 |
| Haiku 4.5 | $0.00007 | $0.00274 |
Grade A, and why
dashboard-design 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 3d 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SOVA Dashboard Design System + Quality Protocol
Read this skill BEFORE writing any template HTML, CSS, or frontend JavaScript under sova/dashboard/. It combines the design system reference with quality-of-execution rules that prevent generic AI output.
0. Reference Files
Before making changes, read these:
sova/dashboard/static/style.css-- CSS variables (Catppuccin Mocha), component classessova/dashboard/templates/_head.html-- shared Tailwind config (centralized)sova/dashboard/templates/_icons.html-- SVG icon macro (Heroicons v2 outline)sova/dashboard/templates/_components.html-- Jinja2 component macros (stat_card, card_header)docs/design-system.md-- full design system reference
1. Design Dials
Three dials control output. SOVA defaults (do not change without explicit user instruction):
| Dial | Value | Effect |
|---|---|---|
| DESIGN_VARIANCE | 3 (Predictable) | Symmetrical grids, equal paddings. Developers need trust, not surprise. |
| MOTION_INTENSITY | 2 (Static) | CSS :hover/:focus only. No scroll-triggered reveals, no auto-animations. Agent status data should feel stable. |
| VISUAL_DENSITY | 6 (Dense App) | Tighter spacing (p-4 to p-8). Dashboard is information-dense by nature. |
These dials mean: no masonry layouts, no parallax, no staggered scroll reveals, no ambient background motion.
2. Anti-Slop Rules (Banned Patterns)
If your generated code includes ANY of these, the output fails quality checks:
Layout
- Generic 3-equal-column grids with identical cards (the "SaaS landing page" look)
- Cards with no visual hierarchy -- all same padding, same font size, same weight
- Full-width sections with no constraint (content stays within the
ml-64 p-8main area) - Centered text blocks wider than
max-w-2xl
Color
- Any color outside Catppuccin Mocha palette (no hardcoded hex, rgb, hsl)
- Gradient backgrounds on containers or sections (SOVA is flat, not glassmorphic)
- Random opacity values -- use the established scale:
text-gray-500for muted,/30for borders,/20for subtle fills,/10for faint backgrounds rgba(0,0,0,...)or similar generic shadows -- use Catppuccin surface colors
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.
- 3d ago First seen · 225 lines · 66 tokens per session scan A c4aeb18942c4
dashboard-design is a skill published in the GitHub repository xsovad06/sova (2 stars, last pushed today), licensed Apache-2.0. It adds 66 tokens to every session and 2,742 once invoked, about $0.0003 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
frontend-design
Use when building any user-facing UI — components, pages, layouts, forms, tables, dashboards, or any feature where visual quality matters. Also triggers for responsive implementation, animation/transitions, design system work, component composition, and design decision-making. This skill makes autonomous design…
design-lead
Your Head of Design + Head of Product-UX. Use this skill whenever a decision is strategic — product structure, interaction philosophy, design-system direction, cross-feature consistency, or any "how should this feel across the product" question. Triggers on: product structure ("is this projekt-zentrisch or…
creative-design
Use when creating new UIs from scratch — landing pages, marketing sites, prototypes, or any greenfield frontend work where no existing design system applies. Also triggers for portfolio sites, product launches, campaign pages, microsites, or any page where visual distinction and memorability matter as much as…
ux-planning
Use when planning a feature from a UI/UX perspective — user flows, screen inventory, information architecture, navigation, and interaction patterns. Use BEFORE implementation, AFTER brainstorming. Also triggers for navigation redesign, onboarding flow design, mobile-first planning, feature scoping from a UX…
bos-code-quality
Ensure all code meets BOS (Brand Operating System) standards for design system compliance, accessibility, and brand consistency. This skill integrates with code reviews to add BOS-specific quality gates.
material-ui-tailwind
Integrates Material UI with Tailwind CSS v4 using cascade layers (enableCssLayer, @layer order) and documents Tailwind v3 interoperability (preflight, important, injectFirst, portals). Use when combining MUI with Tailwind utilities, slotProps className, or theme token bridges.