css-tokens

A command for managing design tokens, which are named values for shared choices such as colors, spacing, fonts, and shadows.

In plain words
What is it for?
Creating token systems, extracting values from CSS, converting formats, applying tokens, checking their use, and syncing them from design tools.
Why use it?
It keeps visual values consistent and makes them easier to reuse or move between CSS, Sass, JavaScript, and JSON.

Command

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/andronics/claude-plugin-css-pro/css-tokens
Clone the repo
git clone --depth 1 https://github.com/andronics/claude-plugin-css-pro
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,296 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.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.02296
Opus 5 $0.00007 $0.01148
Sonnet 5 $0.00003 $0.00459
Haiku 4.5 $0.00001 $0.00230

Measured 2d ago against content hash 560f5081e534, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

css-tokens 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 2d 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.

commands/css-tokens.md · 425 lines

How it starts

The opening of the file, as written. The whole thing — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Token Manager

I'll help you manage design tokens: generate token systems, extract tokens from existing CSS, convert between formats, and apply tokens to your project.

Arguments

/css-tokens [operation] [options]

operation:

  • generate - Create new token system
  • extract - Extract tokens from existing CSS
  • convert - Convert between formats (CSS/Sass/JS/JSON)
  • apply - Apply tokens to CSS files
  • audit - Audit token usage
  • sync - Sync tokens from design tools
  • (omit for interactive mode)

Operations

1. Generate Tokens

Create a complete design token system from scratch.

What I'll create:

tokens/
├── global/
│   ├── colors.css       # Color primitives
│   ├── spacing.css      # Spacing scale
│   ├── typography.css   # Font tokens
│   └── effects.css      # Shadows, transitions
├── semantic/
│   ├── colors.css       # Semantic color tokens
│   └── spacing.css      # Semantic spacing tokens
├── component/
│   ├── button.css       # Button tokens
│   ├── card.css         # Card tokens
│   └── input.css        # Input tokens
└── tokens.css           # Combined output

Token Categories:

Color Tokens
/* Global - Raw color values */
--color-blue-500: #3b82f6;
--color-gray-900: #111827;

/* Semantic - Purpose-based */
--color-primary: var(--color-blue-500);
--color-text-primary: var(--color-gray-900);

/* Component - Specific usage */
--button-bg-primary: var(--color-primary);
Spacing Tokens
/* Global - Base scale */
--spacing-4: 1rem;
--spacing-6: 1.5rem;

/* Semantic - Context */
--spacing-md: var(--spacing-4);
--spacing-lg: var(--spacing-6);

/* Component - Usage */
--button-padding-x: var(--spacing-md);
Typography Tokens
/* Global - Sizes and weights */
--font-size-base: 1rem;
--font-weight-semibold: 600;

/* Semantic - Purpose */
--text-base: var(--font-size-base);
--text-bold: var(--font-weight-semibold);

/* Component - Application */
--button-font-size: var(--text-base);
--button-font-weight: var(--text-bold);

Read the full file on GitHub · 425 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.

  1. 2d ago First seen · 425 lines · 0 tokens per session scan A 560f5081e534

Subscribe to this mod's changes

css-tokens is a command published in the GitHub repository andronics/claude-plugin-css-pro (2 stars, last pushed 10mo ago), licensed MIT. It adds 14 tokens to every session and 2,296 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.

Related

Other commands, from other repositories

kim-ui2code

Kim截图转代码命令 - Gemini看图分析 + Claude技术方案 + Codex代码生成 + Gemini代码审查.

KimYx0207/Claudecode-Codex-Gemini · 25 tokens

bolder

Amplify personality — raises layout variance and motion, strengthens typography and one signature detail, without slop. Use when the UI works but feels safe, flat, or "template-y", or when the user says "bolder", "more personality", "more creative", or "make it pop" (still professional).

educlopez/ui-craft · 64 tokens

polish

Final quality pass: alignment, spacing, consistency, design system adherence, typography, interaction states, and code cleanup. Replaces polish + normalize + distill.

koolamusic/claudefiles · 32 tokens

color-palette

Generate an accessible colour palette from a hex value.

jezweb/claude-skills · 9 tokens

ux-recommend

The v2 flagship. Runs the 5-parallel-search Python engine across 11 data manifests (75+ styles, 170+ palettes, 65+ type pairs, 120+ components, 170+ industries, 110+ UX laws, 50+ motion presets, 120+ anti-patterns, 92 brand specs) and returns a complete recommended design system for your project — with always-on…

Laith0003/ux-skill · 93 tokens

ux-evolve

Auto-iterate the lint→polish→re-lint loop on a generated artifact until score crosses 90 or plateaus. Triggers on "polish this", "evolve this surface", "improve until score 90+", "auto-fix", "run the loop". Use when the user has a freshly generated surface that needs automatic refinement to ship-ready quality. Skip…

Laith0003/ux-skill · 117 tokens