sigil-design

sigil-design is a skill for Claude Code, Codex from Kevin-Liu-01/Sigil-UI. It costs 111 tokens per session (2,892 once invoked), scanned A, original, MIT.

Guidance for creating a DESIGN.md file as the single reference for a project's visual identity. The file can be generated, extracted from a website, audited, and compiled into CSS, Tailwind CSS, and W3C JSON token files.

In plain words
What is it for?
Use it to create or change a visual identity, extract design choices from a reference URL, compile token files, synchronize generated sections, or audit a design against its specification.
Why use it?
It keeps design decisions in one readable source and makes the same values available in several formats. This reduces drift between design documentation and implementation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create or change a visual identity, extract design choices from a reference URL, compile token files, synchronize generated sections, or audit a design against its specification.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kevin-liu-01/sigil-ui/sigil-design
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.

Any agent
npx skills add Kevin-Liu-01/Sigil-UI --skill sigil-design
Clone the repo
git clone --depth 1 https://github.com/Kevin-Liu-01/Sigil-UI

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 sigil-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/kevin-liu-01/sigil-ui/sigil-design/github.svg)](https://agentmods.dev/skills/kevin-liu-01/sigil-ui/sigil-design)
Your own site
<a href="https://agentmods.dev/skills/kevin-liu-01/sigil-ui/sigil-design"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/sigil-ui/sigil-design/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 sigil-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/kevin-liu-01/sigil-ui/sigil-design"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/sigil-ui/sigil-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,892 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 $0.00111 $0.02892
Opus 5 $0.00056 $0.01446
Sonnet 5 $0.00022 $0.00578
Haiku 4.5 $0.00011 $0.00289

Measured 11d ago against content hash 9e98391940e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

sigil-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 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.

skills/sigil-design/SKILL.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill — sigil-design

Generate, parse, and compile a unified DESIGN.md that serves as the single source of truth for a project's visual identity. One file. 33 categories. 519 tokens. Compiles to CSS + Tailwind v4 + W3C JSON.

When to Use

  • Creating a new design reference for a project
  • Extracting a design system from an existing site
  • Switching a project's entire visual identity
  • Generating compiled token output (CSS, Tailwind, JSON)
  • Auditing a design against the spec

CLI Commands

sigil design generate          # Create DESIGN.md from current preset + overrides
sigil design compile           # Parse DESIGN.md → output CSS, Tailwind, JSON files
sigil design sync              # Update Compile sections in-place from token tables
sigil design extract <url>     # Extract full DESIGN.md from a reference URL

Format Specification

File: DESIGN.md

The file is a Markdown document with a strict heading hierarchy. Every section uses GitHub-flavored pipe tables parseable by parseDesignMarkdown(). The file compiles to three output formats from a single source.


Header Block

# {Brand Name} — Style Reference
> {One-line personality tagline.}

**Theme:** light | dark | adaptive
**Preset:** {preset-name} | custom
**Density:** compact | balanced | editorial

{2-4 sentence description of the brand's design language, mood, and aesthetic intent.}

Metadata fields are extracted by regex from bold-label lines.


Section Index (required order)

# Heading Sigil Category Table Format
1 ## Tokens — Colors colors Token | Light | Dark | Role
2 ## Tokens — Typography typography Token | Value | Role
3 ## Tokens — Spacing spacing Token | Value | Role
4 ## Tokens — Layout layout Token | Value | Role
5 ## Tokens — Sigil Grid sigil Token | Value | Role
6 ## Tokens — Radius radius Token | Value | Role
7 ## Tokens — Shadows shadows Token | Value | Role
8 ## Tokens — Motion motion special (subsections)
9 ## Tokens — Borders borders Token | Value | Role
10 ## Tokens — Backgrounds backgrounds Token | Value | Role
11 ## Block Tokens — Buttons buttons Token | Value | Role
12 ## Block Tokens — Cards cards Token | Value | Role
13 ## Block Tokens — Headings headings Token | Value | Role
14 ## Block Tokens — Navigation navigation Token | Value | Role
15 ## Block Tokens — Inputs inputs Token | Value | Role
16 ## Block Tokens — Code code Token | Value | Role
17 ## Block Tokens — Hero hero Token | Value | Role
18 ## Block Tokens — CTA cta Token | Value | Role
19 ## Block Tokens — Footer footer Token | Value | Role
20 ## Block Tokens — Banner banner Token | Value | Role
21 ## Block Tokens — Sections sections Token | Value | Role
22 ## Composition — Page Rhythm pageRhythm Token | Value | Role
23 ## Composition — Grid & Alignment alignment Token | Value | Role
24 ## Composition — Dividers dividers Token | Value | Role
25 ## Composition — Grid Visuals gridVisuals Token | Value | Role
26 ## Composition — Cursor & Scrollbar cursor, scrollbar Token | Value | Role
27 ## Composition — Focus & Overlays focus, overlays Token | Value | Role
28 ## Composition — Data Visualization dataViz Token | Value | Role
29 ## Composition — Media media Token | Value | Role
30 ## Composition — Controls controls Token | Value | Role
31 ## Composition — Component Surfaces componentSurfaces Token | Value | Role
32 ## Components prose (not compiled)
33 ## Surfaces Level | Name | Value | Purpose
34 ## Do's and Don'ts prose (not compiled)
35 ## Imagery prose (not compiled)
36 ## Layout prose (not compiled)
37 ## Similar Brands prose (not compiled)
38 ## Compile — CSS fenced css block
39 ## Compile — Tailwind v4 fenced css block
40 ## Compile — W3C Design Tokens fenced json block

Read the full file on GitHub · 293 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. 11d ago First seen · 293 lines · 111 tokens per session scan A 9e98391940e9

Subscribe to this mod's changes

sigil-design is a skill published in the GitHub repository Kevin-Liu-01/Sigil-UI (9 stars, last pushed 1mo ago), licensed MIT. It adds 111 tokens to every session and 2,892 once invoked, about $0.0006 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 skills, from other repositories

design-system-tokens

Design token management with the W3C Design Token spec, three-tier hierarchy (global/alias/component), OKLCH color, Style Dictionary transforms, and dark mode theming. Use when creating token files, implementing theme systems, or building design-to-code pipelines.

yonatangross/orchestkit · 58 tokens

design-system-architecture

Build scalable design systems with design tokens, component APIs, and documentation. Use when creating or evolving component libraries.

NickCrew/Claude-Cortex · 27 tokens

extract-design

Extract the full design language from any website URL. Produces 8 output files including AI-optimized markdown, visual HTML preview, Tailwind config, React theme, shadcn/ui theme, Figma variables, W3C design tokens, and CSS variables. Also runs WCAG accessibility scoring. Use when user says 'extract design', 'get…

Manavarya09/design-extract · 98 tokens

design-dna

Extract, define, and apply design DNA across three dimensions: design system (tokens), design style (qualitative feel), and visual effects (Canvas, WebGL, 3D, particles, shaders, scroll effects, etc.). Use this skill when: (1) a user wants to see the full 3-dimension design structure/schema, (2) a user provides…

zanwei/design-dna · 192 tokens

designlang-tokens

Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.

Manavarya09/design-extract · 30 tokens

ss-studio

Turn a product brief and optional references into three distinct creative directions, a human-selected StyleSeed interaction plan, generated image/video asset jobs, a working UI prototype, and a verified prototype-first showcase reel. Use for client concepts, app interaction exploration, trendy but coherent UI…

bitjaru/styleseed · 75 tokens