sites-canvas-design

sites-canvas-design is a skill for Claude Code from joaoguirunas/team-os. It costs 73 tokens per session (807 once invoked), scanned A, original, MIT.

A guide to creating complex visual components with HTML5 Canvas and SVG, including charts, illustrations, and custom interface elements.

In plain words
What is it for?
It is for building custom charts, drawings, illustrations, and interactive graphics in websites.
Why use it?
It helps when standard HTML elements are not enough for the required visuals.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit It is for building custom charts, drawings, illustrations, and interactive graphics in websites.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joaoguirunas/team-os/sites-canvas-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 joaoguirunas/team-os --skill sites-canvas-design
Clone the repo
git clone --depth 1 https://github.com/joaoguirunas/team-os

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 sites-canvas-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/joaoguirunas/team-os/sites-canvas-design/github.svg)](https://agentmods.dev/skills/joaoguirunas/team-os/sites-canvas-design)
Your own site
<a href="https://agentmods.dev/skills/joaoguirunas/team-os/sites-canvas-design"><img src="https://agentmods.dev/badge/skills/joaoguirunas/team-os/sites-canvas-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 sites-canvas-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/joaoguirunas/team-os/sites-canvas-design"><img src="https://agentmods.dev/badge/skills/joaoguirunas/team-os/sites-canvas-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 807 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 $0.00073 $0.00807
Opus 5.5 $0.00029 $0.00323
Sonnet 5.5 $0.00015 $0.00161
Haiku 4.5 $0.00007 $0.00081

Measured 12d ago against content hash 3123224525eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sites-canvas-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 12d 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.

.claude/skills/sites-canvas-design/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sites Canvas Design — HTML5 Canvas e SVG

Quando usar Canvas vs SVG

Canvas SVG
Gráficos dinâmicos (dados em tempo real) Ícones e ilustrações estáticas
Efeitos de partículas Animações CSS/SMIL
Jogos e simulações Logos e elementos de marca
Processamento de imagem Diagramas e infográficos

SVG otimizado para web

export function Icon({ className }: { className?: string }) {
  return (
    <svg
      xmlns="http://www.w3.org/2000/svg"
      viewBox="0 0 24 24"
      fill="none"
      stroke="currentColor"
      strokeWidth={2}
      className={cn("h-6 w-6", className)}
      aria-hidden="true"
    >
      <path ... />
    </svg>
  )
}

Backgrounds CSS avançados

Fundo deriva da paleta da marca; gradiente só se a marca pedir. Mesh gradient azul/violeta/rosa e grid de linhas finas cinza atrás do hero são o sinal nº 1 de "cara de IA" — não são padrão aqui. Antes de qualquer fundo decorativo, pergunte o que ele diz sobre o assunto da página; se a resposta for "nada", use cor sólida do token (--color-background, --color-muted) e deixe o conteúdo trabalhar.

/* Fundo tonal da marca — duas paradas da PRÓPRIA paleta, contraste baixo.
   Só use se o sistema visual do projeto previr gradiente. */
.bg-marca {
  background: linear-gradient(180deg, var(--color-background) 0%, var(--color-muted) 100%);
}

/* Padrão geométrico só quando ele vem da identidade (ex.: grade de planta para arquitetura,
   pauta para educação) — traço e cor saem dos tokens, nunca cinza genérico fixo */
.bg-padrao-marca {
  background-image: linear-gradient(to right, var(--color-border) 1px, transparent 1px);
  background-size: var(--padrao-passo, 48px) 100%;
}

/* Noise texture */
.bg-noise::after {
  content: '';
  position: absolute;
  inset: 0;
  background-image: url("data:image/svg+xml,...");
  opacity: 0.04;
}

Canvas — animação de partículas simples

useEffect(() => {
  const canvas = canvasRef.current
  if (!canvas) return
  const ctx = canvas.getContext('2d')
  if (!ctx) return

  let rafId: number
  const animate = () => {
    ctx.clearRect(0, 0, canvas.width, canvas.height)
    particles.forEach(p => { p.update(); p.draw(ctx) })
    rafId = requestAnimationFrame(animate)
  }
  rafId = requestAnimationFrame(animate)

  return () => cancelAnimationFrame(rafId)
}, [])

Read the full file on GitHub · 92 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. 12d ago Changed · +4 lines · +7 tokens per session 3123224525eb
  2. 1mo ago Changed 719d8417c823
  3. 1mo ago Changed · +10 lines · +38 tokens per session 3fa66b2c8731
  4. 2mo ago First seen · 78 lines · 28 tokens per session scan A f591e48b317e

Subscribe to this mod's changes

sites-canvas-design is a skill published in the GitHub repository joaoguirunas/team-os (6 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 807 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 2026-09-03.

Related

Other skills, from other repositories

interaction-skill

Layer A interaction-mechanics reference anchored to the beui.dev catalog. Stacks on any style skill whenever work adds or changes motion or interaction — micro-interactions, animated components, transitions, gestures, hover/press/state feedback, loading/success/error morphs, 'make it feel alive'. Mandates reading the…

code-yeongyu/oh-my-openagent · 104 tokens

layout-skill

Layer A layout-mechanics reference. Stacks on any style skill when the screen is an app shell, dashboard, settings, list-detail, mail/inbox, or any layout with fixed regions plus a scrolling body — or when a layout breaks under long, empty, or unbroken content. Owns spatial structure and scroll ownership; owns zero…

code-yeongyu/oh-my-openagent · 88 tokens

vertical-site-conventions

Compose pages and sites that read as their vertical: ecommerce-catalog storefronts that look like storefronts, hospitality-food sites that look like restaurants, b2b-manufacturer sites that look industrial. Use this skill whenever the user wants to build a site that looks like the vertical it serves, fix a build that…

rampstackco/claude-skills · 190 tokens

responsive-layout-builder

Build responsive layouts with CSS Grid, Flexbox, and container queries. Use when creating responsive designs, fixing layout issues, or building mobile-first layouts.

OneWave-AI/claude-skills · 34 tokens

gsap

Expert guidelines for building high-performance animations with GSAP (GreenSock Animation Platform).

Mindrally/skills · 19 tokens

screenshot-to-code

Turns a screenshot, mockup, Figma export, or photo of a UI into working front-end code - React + Tailwind CSS v4 by default, or Next.js, Vue, or plain HTML/CSS - matching layout, spacing, colors, and typography, then renders the result and compares it against the image to close visual gaps. Use whenever the user…

OneWave-AI/claude-skills · 127 tokens