A coding command that applies the SOVA design system, a set of shared rules for dashboard colors, layouts, components, and icons.

Creating or modifying dashboard UI elements while consulting SOVA's CSS, templates, components, icons, JavaScript utilities, and design documentation.

It helps keep new or changed dashboard screens consistent with the existing SOVA interface instead of introducing unrelated styles.

design — Command by xsovad06

Install

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.

agentmods

npx agentmods add commands/xsovad06/sova/design

Clone the repo

git clone --depth 1 https://github.com/xsovad06/sova

Made for: Claude Code.

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 946 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00015	$0.00946
Opus 5	$0.00008	$0.00473
Sonnet 5	$0.00003	$0.00189
Haiku 4.5	$0.00002	$0.00095

Measured yesterday against content hash eca0e5ed780c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

.claude/commands/design.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SOVA UI Design Standards

Apply the SOVA design system to the specified UI work. Context: $ARGUMENTS

1. Load the Design System

Read these files before making any UI decisions:

sova/dashboard/static/style.css -- CSS variables (Catppuccin Mocha), component classes
sova/dashboard/templates/base.html -- layout, Tailwind config, icon macro, notification panel
sova/dashboard/templates/_head.html -- shared Tailwind config (centralized)
sova/dashboard/templates/_icons.html -- icon macro (Heroicons v2 outline)
sova/dashboard/templates/_components.html -- Jinja2 component macros (stat_card, card_header)
sova/dashboard/static/app.js -- SOVA_COLORS, toast system, browser notifications, shared utilities
docs/design-system.md -- full design system reference

Optionally view the living style guide at /style-guide in the running dashboard.

2. Mandatory Rules

Colors

Every color must come from the Catppuccin Mocha palette defined as CSS variables in style.css
Tailwind classes use RGB vars: bg-accent, text-accent-green, border-accent/30
JS uses window.SOVA_COLORS.accent (populated from CSS vars at init)
Never hardcode hex values in templates or JS
Semantic meanings:
- Blue (accent): primary, links, active state
- Green: success, done, money
- Red: error, failed, danger
- Yellow: warning, running, action needed
- Purple (mauve): metadata, researcher role

Buttons (3 main variants)

Primary: .sova-btn .sova-btn-primary or bg-accent/20 text-accent hover:bg-accent/30
Danger: .sova-btn .sova-btn-danger
Success: .sova-btn .sova-btn-success
Warning: .sova-btn .sova-btn-warning
Never invent new button color combinations

Cards

Container: .sova-card or bg-surface-card rounded-lg border border-gray-700/50
Header: .sova-card-header or use the card_header() macro
Stat: .sova-stat + .sova-stat-label + .sova-stat-value or use the stat_card() macro

Typography (6 roles)

Page heading: text-2xl font-semibold
Section heading: text-lg font-semibold
Label: text-sm font-medium
Body: text-sm (default)
Caption: text-xs text-gray-500
Data/numbers: font-mono font-semibold

Read the full file on GitHub · 85 lines

Changes

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.

yesterday First seen · 85 lines · 15 tokens per session scan A eca0e5ed780c

Subscribe to this mod's changes

design is a command published in the GitHub repository xsovad06/sova (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 15 tokens to every session and 946 once invoked, about $0.0001 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.

Analytics and metrics Code review Frontend ai-agents automation autonomous-development cli developer-tools

design

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

SOVA UI Design Standards

1. Load the Design System

2. Mandatory Rules

Colors

Buttons (3 main variants)

Cards

Typography (6 roles)

What this file has done since we first saw it

Other commands, from other repositories

dashboard

doctor

run

merge

greptile-review

update