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.
git clone --depth 1 https://github.com/jangles-byte/atelierWrote 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/plugins/jangles-byte/atelier/atelier)<a href="https://agentmods.dev/plugins/jangles-byte/atelier/atelier"><img src="https://agentmods.dev/badge/plugins/jangles-byte/atelier/atelier/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/plugins/jangles-byte/atelier/atelier"><img src="https://agentmods.dev/badge/plugins/jangles-byte/atelier/atelier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
atelier 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 1mo 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
{
"name": "atelier",
"displayName": "Atelier",
"version": "0.7.0",
"description": "Generative animation for Claude Code \u2014 flow fields, physarum, strange attractors, boids, reaction-diffusion, domain warping; GPU/WebGL2 GPGPU and raymarched SDFs; density-to-tone mapping, post-processing and art direction. Parameters are machine-verified, and a bundled capture script records the running result so the work gets judged by watching it. Also includes interface-motion recipes.",
"author": {
"name": "Atelier contributors",
"url": "https://github.com/jangles-byte/atelier"
},
"homepage": "https://github.com/jangles-byte/atelier",
"repository": "https://github.com/jangles-byte/atelier",
"license": "MIT",
"keywords": [
"generative",
"generative-art",
"creative-coding",
"animation",
"shaders",
"webgl",
"glsl",
"flow-field",
"particles",
"motion",
"design"
]
}
What it installs
The manifest is a name and a version. 7 skills travel with it, and installing the plugin installs all of them — 966 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json 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.
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.
- 1mo ago First seen · 27 lines scan A cd9c9cb80a5d
atelier is a plugin published in the GitHub repository jangles-byte/atelier (3 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
sheleg-design
SHELEG Design methodology: cinematic scroll-driven landing pages (single scroll clock, layered degrade-to-calm motion, WebGL particle formations), a motion doctrine that decides whether to animate before it decides how, and thirty-nine pluggable visual style packs, each with a ready-made token layer …
iotron-gsap-cookbook
12 GSAP animation skills — production recipes for scroll, text, SVG, cursor, canvas, and visual effects in any framework.
shiny
Collection of skills for Shiny app development.
genjutsu
Genjutsu - the art of illusion for Claude Code and claude.ai. Cast motion and paint visual signatures into Web, Android (Compose), and Apple (SwiftUI) interfaces. Anti-AI-slop creative coding.
superdesign-skill
Design or redesign frontend UI, presentations, and marketing graphics on the Superdesign infinite canvas. Uses approved slide outlines, project context, and branchable drafts you refine.
motiscope
Recreate any web animation from a screen recording. Drop a video of an animation you like, motiscope measures its timing and curates keyframes, and your agent rebuilds it as GSAP, CSS, Framer Motion, or Lottie code. Works in Claude Code, Codex, and Cursor.