canvas-design

canvas-design is a skill for Claude Code, Codex from evoelsewhere/evoflux. It costs 59 tokens per session (511 once invoked), scanned A, original, Apache-2.0.

A skill for creating original static artwork as a PNG image or print-ready PDF. It covers items such as posters, covers, wall art, editorial layouts, and other one-page visual pieces.

In plain words
What is it for?
Use it to make static digital or printable artwork when the result is a single canvas rather than an interactive webpage or generative sketch.
Why use it?
It provides a defined process for deciding the composition, colors, typography, spacing, and focal point of a finished visual.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/evoelsewhere/evoflux/canvas-design
Any agent
npx skills add evoelsewhere/evoflux --skill canvas-design
Clone the repo
git clone --depth 1 https://github.com/evoelsewhere/evoflux

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 canvas-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/evoelsewhere/evoflux/canvas-design.svg)](https://agentmods.dev/skills/evoelsewhere/evoflux/canvas-design)
Your own site
<a href="https://agentmods.dev/skills/evoelsewhere/evoflux/canvas-design"><img src="https://agentmods.dev/badge/skills/evoelsewhere/evoflux/canvas-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 511 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 $0.00059 $0.00511
Opus 5 $0.00030 $0.00255
Sonnet 5 $0.00012 $0.00102
Haiku 4.5 $0.00006 $0.00051

Measured 4d ago against content hash cdf5a68f5f50, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d 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.

app/agent/builtin_skills/canvas-design/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create static canvas artwork

Deliver the requested visual artifact, not a prose manifesto. Build an original composition from the subject, audience, viewing distance, physical or digital format, and one deliberate visual thesis. Do not load the bundled font library when this skill activates.

State machine

1. FRAME

Confirm canvas size, orientation, output format, required text, brand or legal constraints, and whether the work is primarily expressive or informational. Infer non-blocking choices from the brief. Ask only when missing dimensions, copy, or brand assets would materially change the deliverable.

2. DIRECT

Define a compact visual system before production:

  • one compositional idea and focal point;
  • palette with functional roles;
  • type roles and hierarchy when text is required;
  • grid, margins, rhythm, and intended negative space;
  • one signature element tied to the subject.

Translate artist references into general visual attributes; do not copy a recognizable work or imitate a living artist. Use text as content, not filler, and never invent event, legal, pricing, or contact details.

3. BUILD

Create only the formats requested. Use vector or code-native geometry where it improves print quality. Inspect canvas-fonts/ only after choosing required type roles, then load the minimum matching font files and retain their license files. Keep all content inside safe margins and make typography readable at the intended viewing size.

4. VERIFY

Render the final PNG/PDF and inspect the actual image. Check dimensions, resolution, crop/bleed requirements, contrast, text accuracy, font rendering, alignment, clipping, unintended overlap, and export artifacts. Make a second pass that removes or refines weak elements instead of adding decoration.

Stop conditions

Stop when the composition has a clear focal hierarchy, all required copy is accurate, the rendered output is clean at normal and zoomed viewing, and the delivered files match the requested dimensions and formats.

Read the full file on GitHub · 62 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 62 lines · 59 tokens per session scan A cdf5a68f5f50

Subscribe to this mod's changes

canvas-design is a skill published in the GitHub repository evoelsewhere/evoflux (5 stars, last pushed 7d ago), licensed Apache-2.0. It adds 59 tokens to every session and 511 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.