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 aiatelie/ai-atelie --skill canvas-syncgit clone --depth 1 https://github.com/aiatelie/ai-atelieWrote 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/aiatelie/ai-atelie/canvas-sync)<a href="https://agentmods.dev/skills/aiatelie/ai-atelie/canvas-sync"><img src="https://agentmods.dev/badge/skills/aiatelie/ai-atelie/canvas-sync/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/aiatelie/ai-atelie/canvas-sync"><img src="https://agentmods.dev/badge/skills/aiatelie/ai-atelie/canvas-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00147 | $0.02484 |
| Opus 5 | $0.00073 | $0.01242 |
| Sonnet 5 | $0.00029 | $0.00497 |
| Haiku 4.5 | $0.00015 | $0.00248 |
Grade A, and why
canvas-sync 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
canvas-sync
A contributor workflow for AI Atelie. The DesignCanvas surface (the pannable, zoomable workspace that wraps every project's content) lives in three places at once, and a change to one without the others is almost always a bug.
This skill is dev-time only. It does not load into adapter sessions spawned by the editor.
The three places, and what each one is for
| Location | Role | Loaded when |
|---|---|---|
mcp/starters/DesignCanvas.jsx |
Canonical source of truth. The starter the agent copies via mcp__starters__copy_starter and the route POST /api/projects/create reads to seed every new project. |
An agent calls copy_starter in an existing project · A user creates a new project. |
web/projects/demo/design-canvas.jsx |
Demo project's copy. The "AI Atelie demo" project that ships in the repo and renders on first run. | A user opens the demo from /projects (e.g. via home-shows-demo journey, or anyone testing locally). |
web/src/lib/tweakBridge.ts + mcp/CANVAS_PROTOCOL.md |
Host-side wiring. The parent's listener for __page_is_canvas, the __dc_set_theme broadcast, and the documented protocol contract. |
The editor mounts an iframe that announces __page_is_canvas. |
The parity rule
The two .jsx files MUST be byte-identical at every commit. They are not "two copies that drift" — they are two materializations of one source. Verify with:
md5 mcp/starters/DesignCanvas.jsx web/projects/demo/design-canvas.jsx
# (Linux: md5sum)
The two hashes must match. If they don't, stop and reconcile before committing.
The flow direction
Always edit the canonical first, then mirror — never the other way around. The canonical is the file every NEW project copies; the demo is just a testbed.
# 1. Edit the canonical
$EDITOR mcp/starters/DesignCanvas.jsx
# 2. Mirror to the demo
cp mcp/starters/DesignCanvas.jsx web/projects/demo/design-canvas.jsx
# 3. Verify they match
md5 mcp/starters/DesignCanvas.jsx web/projects/demo/design-canvas.jsx
# 4. Both files go in the same commit
git add mcp/starters/DesignCanvas.jsx web/projects/demo/design-canvas.jsx
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.
- 12d ago First seen · 115 lines · 147 tokens per session scan A 435f14c8bfe1
canvas-sync is a skill published in the GitHub repository aiatelie/ai-atelie (8 stars, last pushed 3mo ago), licensed MIT. It adds 147 tokens to every session and 2,484 once invoked, about $0.0007 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.
Other skills, from other repositories
waitlist-page
Minimal pre-launch landing with email capture, brand logo, and optional decorative layer. Reads DESIGN.md for colors, typography, and layout rules. Best for: product launches, beta signups, early access programs, indie projects.
saas-landing
Single-page SaaS landing with hero, features, social proof, pricing, and CTA. Respects the active DESIGN.md color/typography/layout tokens. Trigger keywords: "saas landing", "marketing page", "product landing".
web-prototype
General-purpose desktop web prototype. Single self-contained HTML file built by copying the seed assets/template.html and pasting section layouts from references/layouts.md. Default for any landing / marketing / docs / SaaS page when no more specific skill matches.
webgl-experience
A full-screen, real-time WebGL/WebGL2 experience — animated shaders, 3D scenes, generative visuals, particle fields — rendered live on the GPU with a typographic overlay. Produced as a single self-contained index.html. Use when the brief asks for a "WebGL", "shader", "3D", "generative", "GPU", "interactive canvas"…
worker-visualizer
A real-time data/particle/simulation visualizer whose heavy compute runs in a Web Worker (off the main thread), optionally sharing memory with the UI via SharedArrayBuffer, and renders to a canvas at 60fps. Produced as a single self-contained index.html. Use when the brief asks for a "web worker", "simulation"…
webgl-liquid-metal
A real-time liquid-metal shader — a domain-warped noise field shaded as molten chrome, with a sweeping specular highlight over an iridescent thin-film (cosine-palette) sheen. No textures. Rendered as a single self-contained index.html. Use when the brief asks for "liquid metal", "molten chrome", "iridescent"…