infinite-canvas is an open-source visual workspace for AI image creation, combining an infinite canvas with image generation, reference-image editing, video generation, chat-based assistance, prompt storage, asset management, and multi-agent workflows. It is for exploring and iterating on visual concepts through a graphical creative process, with access to OpenAI-compatible model services. The catalogue contains skills, an MCP integration, and an instruction for working with the project.
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.
npx skills add basketikun/infinite-canvas --skill open-canvasgit clone --depth 1 https://github.com/basketikun/infinite-canvasWrote 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.
[](https://agentmods.dev/skills/basketikun/infinite-canvas/open-canvas)<a href="https://agentmods.dev/skills/basketikun/infinite-canvas/open-canvas"><img src="https://agentmods.dev/badge/skills/basketikun/infinite-canvas/open-canvas/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.
<a href="https://agentmods.dev/skills/basketikun/infinite-canvas/open-canvas"><img src="https://agentmods.dev/badge/skills/basketikun/infinite-canvas/open-canvas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 15 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 39 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 50 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00038 | $0.00434 |
| Opus 5 | $0.00019 | $0.00217 |
| Sonnet 5 | $0.00008 | $0.00087 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
open-canvas 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 8d 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.
What it actually says
Open Infinite Canvas
默认打开在线版。只有用户明确要求使用本地项目时，才启动本地前端。
在线版
- 启动本地 Canvas Agent 并保持运行：
npx -y @basketikun/canvas-agent@latest
-
从启动输出取得
Local URL和Connect token。 -
在 Codex 右侧浏览器打开：
https://canvas.best/canvas?mode=new#agentUrl=<Local URL>&agentToken=<Connect token>
本地版
- 在 Infinite Canvas 项目中启动前端，并使用 Vite 输出的
Local地址：
cd web
bun install
bun run dev
- 启动本地 Canvas Agent：
npx -y @basketikun/canvas-agent@latest
- 从启动输出取得
Local URL和Connect token，在 Codex 右侧浏览器打开：
<Vite Local 地址>/canvas?mode=new#agentUrl=<Local URL>&agentToken=<Connect token>
MCP 与连接地址
插件在新的 Codex 任务中加载时会自动启动 npx -y @basketikun/canvas-agent@latest mcp。这个 MCP 进程负责提供画布工具，不提供网页连接服务；
上面启动的普通 Canvas Agent 负责提供 Local URL 和 Connect token。两个进程读取同一份本地配置，因此不需要用户手动填写地址或 token。
打开模式
用户没有明确指定打开方式时，始终使用 mode=new 新建画布。只有用户明确要求时才替换为：
- 最近画布：
mode=recent - 自己选择：
mode=choose
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.
- 8d ago Changed 12ca3401c837
- 12d ago First seen · 59 lines · 38 tokens per session scan A a7c12b08dc1c
open-canvas is a skill published in the GitHub repository basketikun/infinite-canvas (6,393 stars, last pushed 5d ago), licensed MIT. It adds 38 tokens to every session and 434 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.