onchainai: Skill for Claude Code

.agents/skills/design-tokens/SKILL.md

design-tokens is a skill for Claude Code, Codex from Coinyak/onchainai. It costs 60 tokens per session (3,666 once invoked), scanned A, original, MIT.

A system for defining consistent design values such as font sizes, colors, spacing, contrast, and dark-mode variants. It produces reusable CSS variables, Tailwind settings, or JSON tokens from explicit formulas.

In plain words
What is it for?
Use it when starting or refining a design system, Tailwind theme, or CSS theme, including type scales, color palettes, spacing grids, and dark mode.
Why use it?
It replaces ad-hoc visual choices with a repeatable scale and checks text colors against WCAG accessibility contrast requirements.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is Coinyak/onchainai's own configuration. It tells Claude Code and Codex how to work on onchainai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything onchainai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Coinyak/onchainai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Coinyak/onchainai/main/.agents/skills/design-tokens/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Coinyak/onchainai

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for design-tokens

README.md
[![agentmods](https://agentmods.dev/badge/skills/coinyak/onchainai/design-tokens/github.svg)](https://agentmods.dev/skills/coinyak/onchainai/design-tokens)
Your own site
<a href="https://agentmods.dev/skills/coinyak/onchainai/design-tokens"><img src="https://agentmods.dev/badge/skills/coinyak/onchainai/design-tokens/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.

agentmods 80×15 button for design-tokens

Your own site · 80×15
<a href="https://agentmods.dev/skills/coinyak/onchainai/design-tokens"><img src="https://agentmods.dev/badge/skills/coinyak/onchainai/design-tokens.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,666 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00060 $0.03666
Opus 5 $0.00030 $0.01833
Sonnet 5 $0.00012 $0.00733
Haiku 4.5 $0.00006 $0.00367

Measured 11d ago against content hash 354a9f8c090f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

design-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 11d 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.

.agents/skills/design-tokens/SKILL.md · 419 lines

How it starts

The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Tokens

Generate type scales, color palettes, spacing systems, and dark mode derivations with math — not guessing. Includes WCAG contrast checking, systematic spacing grids, and production-ready CSS/Tailwind output.

When to Use

  • User is setting up a new project's design system
  • User asks for a type scale, color palette, or spacing system
  • User needs WCAG-compliant color combinations
  • User wants dark mode colors derived from a light palette
  • User asks for "design tokens" or "theme setup"
  • Building a Tailwind config or CSS custom properties

Core Philosophy

  • Math over taste. Scales should follow ratios, not arbitrary values.
  • Accessibility by default. Every text/background combo must pass WCAG AA.
  • Systematic. Every value should be derivable from a base + ratio.
  • Portable. Output as CSS custom properties, Tailwind config, or JSON tokens.

Type Scale Generation

The Formula

fontSize = baseFontSize × ratio^step

Recommended Ratios

Ratio Name Value Best for
Minor Second 1.067 Tight, minimal difference Dense UI, dashboards
Major Second 1.125 Subtle progression Apps, data-heavy interfaces
Minor Third 1.200 Balanced, versatile Most websites, SaaS
Major Third 1.250 Clear hierarchy Marketing sites, blogs
Perfect Fourth 1.333 Strong contrast Editorial, landing pages
Augmented Fourth 1.414 Dramatic Bold designs, portfolios
Perfect Fifth 1.500 Very dramatic Hero-heavy designs

Generating the Scale

Given a base size (typically 16px) and a ratio:

Step -2: 16 / ratio² = xs
Step -1: 16 / ratio  = sm
Step  0: 16          = base
Step  1: 16 × ratio  = lg
Step  2: 16 × ratio² = xl
Step  3: 16 × ratio³ = 2xl
Step  4: 16 × ratio⁴ = 3xl
Step  5: 16 × ratio⁵ = 4xl
Step  6: 16 × ratio⁶ = 5xl

Round to nearest 0.5px or convert to rem (÷ 16).

Line Height Rules

Font Size Line Height Use
≤ 14px 1.6–1.7 Small text, captions
16–20px 1.5–1.6 Body text
20–32px 1.3–1.4 Subheadings
32–48px 1.1–1.2 Headings
48px+ 1.0–1.1 Display/hero text

Read the full file on GitHub · 419 lines

Files

What ships with it

1 file 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.

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. 11d ago First seen · 419 lines · 60 tokens per session scan A 354a9f8c090f

Subscribe to this mod's changes

design-tokens is a skill published in the GitHub repository Coinyak/onchainai (1 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 3,666 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.