generate-tokens

generate-tokens is a skill for Claude Code from realmpastai-web/claude-design-suite. It costs 74 tokens per session (532 once invoked), scanned A, original, MIT.

A tool that converts a design description into a W3C Design Tokens JSON file. Design tokens are reusable values such as colors, font settings, spacing, shadows, and animation timings.

In plain words
What is it for?
It helps generate tokens for Style Dictionary, Tokens Studio, Figma, or code-generation pipelines.
Why use it?
It avoids manually copying design values into a format that design and code tools can share.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/generate_tokens.py <source> --out tokens/tokens.json --format w3c.

Part of the brand-intelligence plugin — 8 skills, 4 commands shipped together

Good fit It helps generate tokens for Style Dictionary, Tokens Studio, Figma, or code-generation pipelines.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/realmpastai-web/claude-design-suite
agentmods
npx agentmods add skills/realmpastai-web/claude-design-suite/generate-tokens

Made for: Claude Code.

Or install brand-intelligence, the plugin that ships this one along with the rest of its 8 skills, 4 commands.

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 generate-tokens

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/realmpastai-web/claude-design-suite/generate-tokens"><img src="https://agentmods.dev/badge/skills/realmpastai-web/claude-design-suite/generate-tokens.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 532 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 $0.00074 $0.00532
Opus 5.5 $0.00030 $0.00213
Sonnet 5.5 $0.00015 $0.00106
Haiku 4.5 $0.00007 $0.00053

Measured 2mo ago against content hash dbecd9ae95c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

generate-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 2mo 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.

plugins/brand-intelligence/skills/generate-tokens/SKILL.md · 43 lines

What it actually says

Generate Tokens

Context

You are emitting a W3C Design Tokens JSON file from $ARGUMENTS (a DESIGN.md path or "current" = the most recent compose output).

Domain Context

  • W3C Design Tokens spec uses { "$value": "...", "$type": "color|dimension|fontFamily|duration|..." } — follow it precisely or downstream tools break.
  • Tokens group into: color, typography, spacing, radius, shadow, motion, zIndex.
  • Aliases are allowed and encouraged: {color.brand.500} → referenced from button.background.

Instructions

  1. Parse the source (a DESIGN.md or a design-system/MASTER.md).
  2. Extract: palette (with light + dark), typography stack, type scale, spacing scale, radii, shadows, motion defaults.
  3. Run:
    python scripts/generate_tokens.py <source> --out tokens/tokens.json --format w3c
    
  4. The script writes a W3C-compliant JSON. Verify it by re-parsing and summarizing counts (12 colors, 6 typography variants, 8 spacing stops, 5 radii, 3 shadows, 4 motion).
  5. Optionally emit sibling files with --format <target>:
    • style-dictionary → emits tokens.style-dictionary.json for Style Dictionary
    • tokens-studio → emits the Tokens Studio flavor
    • tailwind (via sibling skill generate-tailwind)
    • shadcn (via sibling skill generate-shadcn-theme)
  6. Print a sample "consume from code" snippet:
    import tokens from "./tokens/tokens.json";
    const primary = tokens.color.brand["500"].$value;
    

Further Reading

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. 2mo ago First seen · 43 lines · 74 tokens per session scan A dbecd9ae95c1

Subscribe to this mod's changes

generate-tokens is a skill published in the GitHub repository realmpastai-web/claude-design-suite (2 stars, last pushed 6mo ago), licensed MIT. It adds 74 tokens to every session and 532 once invoked, about $0.0003 per session on Opus 5.5. 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

generate-tokens compared with skills from other repositories

generate-tokens next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
generate-tokensrealmpastai-web/claude-design-suiteSkill26mo agoMITA74Claude Code
anti-slop-designsickn33/agentic-awesome-skillsSkill49kyesterdayMITA34Claude Code
chakra-ui-builderchakra-ui/chakra-uiSkill41k3d agoMITA214Claude Code, Codex
visual-ralphYeachan-Heo/oh-my-codexSkill34ktodayMITA52Codex
open-design-setupcompozy/compozySkill2.9ktodayMITA67Claude Code, Codex
prototype-webnexu-io/html-anythingSkill9.5ktodayApache-2.0A24Claude Code, Codex
frontend-visual-qadaymade/claude-code-skillsSkill1.5kyesterdayMITA125Claude Code, Codex