seed: Skill for Claude Code

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

pencil-design is a skill for Claude Code, Codex from seed-hypermedia/seed. It costs 67 tokens per session (2,671 once invoked), scanned A, original, Apache-2.0.

Instructions for designing interfaces in Pencil files and turning those designs into production code.

In plain words
What is it for?
Use it for Pencil-based screen and component design, design-system work, design-to-code tasks, and syncing design choices with frontend code.
Why use it?
It helps keep designs consistent by reusing existing components and design tokens before generating implementation code.

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 seed-hypermedia/seed's own configuration. It tells Claude Code and Codex how to work on seed 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 seed configures →

Reuse

Borrowing it

Nothing to install: this file belongs to seed-hypermedia/seed. 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/seed-hypermedia/seed/main/.agents/skills/pencil-design/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/seed-hypermedia/seed

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 pencil-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/seed-hypermedia/seed/pencil-design.svg)](https://agentmods.dev/skills/seed-hypermedia/seed/pencil-design)
Your own site
<a href="https://agentmods.dev/skills/seed-hypermedia/seed/pencil-design"><img src="https://agentmods.dev/badge/skills/seed-hypermedia/seed/pencil-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,671 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 $0.00067 $0.02671
Opus 5 $0.00034 $0.01336
Sonnet 5 $0.00013 $0.00534
Haiku 4.5 $0.00007 $0.00267

Measured 6d ago against content hash e91fe209826a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pencil-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 6d 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/pencil-design/SKILL.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pencil Design Skill

Design production-quality UIs in Pencil and generate clean, maintainable code from them. This skill enforces best practices for design system reuse, variable usage, layout correctness, visual verification, and design-to-code workflows.

When to Use This Skill

  • Designing screens, pages, or components in a .pen file
  • Generating code (React, Next.js, Vue, Svelte, HTML/CSS) from Pencil designs
  • Building or extending a design system in Pencil
  • Syncing design tokens between Pencil and code (Tailwind v4 @theme, shadcn/ui tokens)
  • Importing existing code into Pencil designs
  • Working with any Pencil MCP tools (pencil_batch_design, pencil_batch_get, etc.)

Critical Rules

These rules address the most common agent mistakes. Violating them produces designs that are inconsistent, hard to maintain, and generate poor code.

Rule 1: Always Reuse Design System Components

NEVER recreate a component from scratch when one already exists in the design file.

Before inserting any element, you MUST:

  1. Call pencil_batch_get with patterns: [{ reusable: true }] to list all available reusable components
  2. Search the results for a component that matches what you need (button, card, input, nav, etc.)
  3. If a match exists, insert it as a ref instance using I(parent, { type: "ref", ref: "<componentId>" })
  4. Customize the instance by updating its descendants with U(instanceId + "/childId", { ... })
  5. Only create a new component from scratch if no suitable reusable component exists

See references/design-system-components.md for detailed workflow.

Rule 2: Always Use Variables Instead of Hardcoded Values

NEVER hardcode colors, border radius, spacing, or typography values when variables exist.

Before applying any style value, you MUST:

  1. Call pencil_get_variables to read all defined design tokens
  2. Map your intended values to existing variables (e.g., use primary not #3b82f6, use radius-md not 6)
  3. Apply values using variable references, not raw values
  4. When generating code, use Tailwind v4 semantic utility classes (e.g., bg-primary, text-foreground, rounded-md). NEVER use arbitrary value syntax (bg-[#3b82f6], text-[var(--primary)], rounded-[6px])

Read the full file on GitHub · 196 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. 6d ago First seen · 196 lines · 67 tokens per session scan A e91fe209826a

Subscribe to this mod's changes

pencil-design is a skill published in the GitHub repository seed-hypermedia/seed (56 stars, last pushed today), licensed Apache-2.0. It adds 67 tokens to every session and 2,671 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.

Related

Other skills, from other repositories

chakra-ui-builder

Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…

chakra-ui/chakra-ui · 214 tokens

frontend-ui-dark-ts

Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.

microsoft/skills · 48 tokens

reveal-hover-effect

Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…

MengTo/Skills · 66 tokens

frontend-visual-qa

Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…

daymade/claude-code-skills · 145 tokens

better-colors

Helps you build a color system and answer anything about color in your project. You can generate palettes, use semantic tokens, convert between formats, check contrast and more.

jakubkrehel/skills · 38 tokens

prototype-web

A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.

nexu-io/html-anything · 24 tokens