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/IamK77/SkillWrote 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/iamk77/skill/atelier)<a href="https://agentmods.dev/plugins/iamk77/skill/atelier"><img src="https://agentmods.dev/badge/plugins/iamk77/skill/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/iamk77/skill/atelier"><img src="https://agentmods.dev/badge/plugins/iamk77/skill/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 27d 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",
"description": "Seven peer creative lenses: canon, color, type, layout, form, graphics, and motion. Systems is an SOP for implementing a selected direction as tokens and components. Pilot is the router. Canon is not a universal prerequisite; design probes are optional instruments, not taste certificates.",
"source": "./",
"strict": false,
"skills": [
"./skills/atelier/pilot",
"./skills/atelier/canon",
"./skills/atelier/color",
"./skills/atelier/type",
"./skills/atelier/layout",
"./skills/atelier/form",
"./skills/atelier/graphics",
"./skills/atelier/motion",
"./skills/atelier/systems"
]
}What it installs
The manifest is a name and a version. 9 skills travel with it, and installing the plugin installs all of them — 301 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 marketplace.json#atelier 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.
- 27d ago Changed 7bf0c6a5094e
- 1mo ago First seen · 17 lines scan A 72336205ae78
atelier is a plugin published in the GitHub repository IamK77/Skill (2 stars, last pushed 5d ago), licensed Apache-2.0. 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 2026-09-03.
Other plugins, from other repositories
design-mastery
Design principles, legendary designers, and historical movements applied to UI work, with agents and workflows for brand identity, design audits, style guides, and premium landing pages.
claude-skills-library marketplace
FrankX multi-brand plugin marketplace: the Agent Skills library plus validated brand packs for GenCreator creators and Starlight Academy.
a11y-audit
Full accessibility audit with WCAG compliance checking.
aio-visual-diff
Verify AI-built UI against design via measurement-driven diff — extracts computed CSS and bounding boxes through Chrome DevTools MCP, diffs against Figma reference or a frozen baseline, and feeds numerical deltas back to the agent. No screenshot eyeballing.
draw-c4
Generate or update an interactive, self-contained C4-style architecture diagram (single HTML file) from a codebase.
ui-structure-skills
Navigation, layout, and timeline components for app structure and organization.