design-token-lock

design-token-lock is a skill for Claude Code from PMDevSolutions/Aurelius. It costs 70 tokens per session (3,020 once invoked), scanned A, original, MIT.

A design-token tool that reads exact values from a Figma design and saves them in a versioned lockfile. It also creates Tailwind configuration and CSS variables from that file; design tokens are shared values such as colors, fonts, and spacing.

In plain words
What is it for?
Extracting colors, typography, spacing, layout gaps, and other values from Figma, then generating files for a Tailwind-based interface. It can also support checks that components use the locked values.
Why use it?
It keeps the coded interface aligned with the Figma design and provides one source of truth when designs change. This helps prevent style drift, where the design and code gradually use different values.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is node scripts/renderer-registry.js resolve <renderer> --json.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

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-token-lock

README.md
[![agentmods](https://agentmods.dev/badge/skills/pmdevsolutions/aurelius/design-token-lock.svg)](https://agentmods.dev/skills/pmdevsolutions/aurelius/design-token-lock)
Your own site
<a href="https://agentmods.dev/skills/pmdevsolutions/aurelius/design-token-lock"><img src="https://agentmods.dev/badge/skills/pmdevsolutions/aurelius/design-token-lock.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,020 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 5.1 $0.00070 $0.03020
Opus 5 $0.00035 $0.01510
Sonnet 5 $0.00014 $0.00604
Haiku 4.5 $0.00007 $0.00302

Measured yesterday against content hash 9a01cd74cbb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

design-token-lock 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/skills/design-token-lock/SKILL.md · 280 lines

How it starts

The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Token Lock — Single Source of Truth

Purpose

Solve the #1 recurring pain point in Figma-to-code: style drift. This skill extracts every design value from Figma, writes a versioned lockfile (design-tokens.lock.json), and generates Tailwind config + CSS custom properties from it. The lockfile becomes the single source of truth — tests assert against it, components reference it, and the verify-tokens script enforces it.

When to Use

  • Phase 2 of the /build-from-figma pipeline (after figma-intake)
  • Any time you need to extract or refresh design tokens from Figma
  • When regenerating Tailwind config from a Figma file

Inputs

  • Required: Figma file key (from build-spec.json or URL)
  • Optional: .claude/plans/build-spec.json (for component-specific token scoping)

Process

Step 1: Extract Tokens from Figma

Call Figma MCP to get all design values:

1. get_variable_defs(fileKey)
   → Color variables, typography variables, spacing variables
   → Variable collections and modes (light/dark)

2. get_design_context(fileKey, nodeId) — for each top-level frame
   → Computed styles on actual elements
   → Auto-layout padding, gap, corner radius values
   → Text styles with exact font-family, size, weight, lineHeight

3. get_screenshot(fileKey, nodeId) — for color reference verification
   → Visual reference to cross-check extracted values

Step 2: Build Token Structure

Organize extracted values into a normalized structure. Every value must trace back to Figma.

Color tokens:

  • Extract from Figma variables first (most accurate)
  • Fall back to computed styles on elements if no variables defined
  • Record: hex, rgb, hsl, and suggested Tailwind class name
  • Group: primitives (raw values), semantic (roles), component-specific

Typography tokens:

  • Font family with full fallback stack
  • Size scale in px and rem (assuming 16px base)
  • Weight values (numeric, not named)
  • Line height as unitless ratio
  • Letter spacing in em

Read the full file on GitHub · 280 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. yesterday First seen · 280 lines · 0 tokens per session scan A 9a01cd74cbb9

Subscribe to this mod's changes

design-token-lock is a skill published in the GitHub repository PMDevSolutions/Aurelius (8 stars, last pushed 21d ago), licensed MIT. It adds 70 tokens to every session and 3,020 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 2026-09-04.

Related

Other skills, from other repositories

figma-design-handoff

Figma-to-code design handoff patterns including Figma Variables to design tokens pipeline, component spec extraction, Dev Mode inspection, Auto Layout to CSS Flexbox/Grid mapping, and visual regression with Applitools. Use when converting Figma designs to code, documenting component specs, setting up design-dev…

yonatangross/orchestkit · 76 tokens

mk:figma

Read-first Figma gateway via Figma MCP: analyze designs, implement Figma-to-code for 1–3 screens, extract design tokens, produce a Figma Evidence Packet for planning handoff, screenshot fallback. Advanced operations (Code Connect, canvas writes, design-system/library patterns) are gated references loaded only on…

ngocsangyem/MeowKit · 99 tokens

generate-project-design-system

현재 프로젝트의 디자인 시스템을 분석하여 project-design-system 스킬의 초안을 생성합니다. Figma MCP의 createdesignsystemrules와 getvariabledefs를 활용하고, 코드베이스를 분석하여 Figma 토큰 → 코드 매핑 규칙을 도출합니다. 초안 생성 후 /skill-creator와 사용자 피드백으로 다듬는 과정이 필요합니다. "디자인 시스템 스킬 만들어줘", "project-design-system 생성" 같은 요청에 사용하세요.

naver/design-to-ui · 105 tokens

mcp-sdk-audit

Upgrade @modelcontextprotocol/server (the MCP TypeScript SDK v2) and prove the wire contract survived. The SDK is a runtime dependency whose breakage lands on the wire, not in the type checker — so this sorts each release by which SDK source files it touched (Figwright uses only the server + stdio slice of a…

awdr74100/figwright · 159 tokens

figma-codegen

Generate framework-aware code from a Figma design. Reads the project's stack profile and emits code matching the existing framework (React/Vue/Svelte/Next/etc.) and styling (Tailwind/CSS/CSS-in-JS), reusing existing components and design tokens instead of regenerating from scratch. Triggers whenever the user wants a…

awdr74100/figwright · 145 tokens

figma-build

Build a Figma design from code or a description — the reverse of figma-codegen. Reuses the connected file's existing design system (components, variables, styles) instead of drawing primitives with hardcoded values. Triggers whenever the user wants something created or updated IN Figma from code or a spec — e.g.…

awdr74100/figwright · 180 tokens