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.
/plugin marketplace add cubha/claude-workflow-pluginsnpx agentmods add plugins/cubha/claude-workflow-plugins/design-lintgit clone --depth 1 https://github.com/cubha/claude-workflow-pluginsGrade A, and why
design-lint 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 2d 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": "design-lint",
"version": "1.0.0",
"description": "Deterministic (no-LLM) design anti-pattern linter with 47 detectors for token hygiene, color/font/spacing consistency, and AI-default clichés (beige backgrounds, text gradients, uppercase eyebrows). Same input always yields the same verdict at zero token cost, so it doubles as a CI gate (--gate).",
"author": {
"name": "cubha"
}
}
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.
- 2d ago First seen · 9 lines scan A 8fb5e85f6e81
design-lint is a plugin published in the GitHub repository cubha/claude-workflow-plugins (2 stars, last pushed 1mo 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
wondelai-skills marketplace
Wondel.ai Agent Skills — Business, Marketing, UX & Coding Frameworks from Bestselling Books. 65 skills for product strategy, UX design, marketing, sales, motivation, conversion optimization, code quality, and systems architecture, plus 14 guided-journey metaskills that orchestrate them step by step.
peekaboo-macos-validator
Runtime observation, interaction, and visual critique for native macOS interfaces via Peekaboo.
ui-clone-skills
Motion forensics for the animated web. Four jobs against a live URL: decode (analyse motion + build, no code), clone (URL → React + Tailwind), verify (AE/SSIM + motion-parity score vs. an existing impl), extract (raw JSON dump). Extracts real CSS and animation params (GSAP / Framer Motion / Lenis / anime.js) directly…
frontend-design
Production-grade frontend design skill that avoids AI slop — specific rules for typography, color (OKLCH), layout, motion, interaction, and UX writing.
cad-design
Parametric CAD design disciplines for makers, mechanical engineers, and product designers. 5 skills covering CAD API scripting (Fusion 360, OpenSCAD, commercial platforms), parametric construction workflows, mechanical design principles (overhangs, walls, tool-less assembly), image-to-mesh-CAD pipelines, and the…
ux-design
Guide, measure, and implement UX best practices in Claude Code. Scored usability + accessibility audits, quantitative UX metrics, and stack-adaptive scaffolding for design tokens, accessible components, interaction feedback, and UX copy.