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 madebyaris/advance-minimax-m3-cursor-rules --skill anti-slop-designgit clone --depth 1 https://github.com/madebyaris/advance-minimax-m3-cursor-rulesWrote 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/madebyaris/advance-minimax-m3-cursor-rules/anti-slop-design)<a href="https://agentmods.dev/skills/madebyaris/advance-minimax-m3-cursor-rules/anti-slop-design"><img src="https://agentmods.dev/badge/skills/madebyaris/advance-minimax-m3-cursor-rules/anti-slop-design/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/madebyaris/advance-minimax-m3-cursor-rules/anti-slop-design"><img src="https://agentmods.dev/badge/skills/madebyaris/advance-minimax-m3-cursor-rules/anti-slop-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00078 | $0.08345 |
| Opus 5 | $0.00039 | $0.04172 |
| Sonnet 5 | $0.00016 | $0.01669 |
| Haiku 4.5 | $0.00008 | $0.00834 |
Grade A, and why
anti-slop-design 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 — 555 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anti-Slop Design Skill ("Taste Layer")
Build UIs that look like a senior designer made them, not a language model. This skill enforces category-aware design thinking, concrete palettes, and a pre-delivery quality gate.
When to Use
- Building any UI: landing page, dashboard, app screen, marketing site
- User asks to "design", "build a page", "create a component", or "make it look good"
- User asks to "create a design system" or "set up design tokens"
- Reviewing or improving existing UI code
For full pages or multi-section layouts, also read reference.md in this skill directory. It contains section anatomy patterns, extended slop catalog, microcopy examples, stack-specific notes, common mistakes per category, CSS token starters, and a mobile-first checklist. Skip it for single-component work.
Step 0: Read Design Context
Before designing anything, inspect the project:
- Check the package manifest for styling approach (Tailwind, CSS Modules, styled-components, vanilla CSS).
- Check for existing design tokens:
tailwind.config.*,theme.ts, CSS variable files,globals.css. - Check for existing font imports (Google Fonts
@import,next/font,@font-face). - Check for an existing icon library (lucide-react, heroicons, phosphor, etc.).
- If a design system already exists, respect it. Extend, do not replace.
Skip this step only for standalone demos or canvases with no project context.
Step 1: Design Thinking
Before writing any UI code, commit to a direction. Never skip this.
- Pick the register. Every surface is brand (marketing, landing, campaign, portfolio -- design IS the product) or product (app UI, dashboard, admin, tool -- design SERVES the task). Brand surfaces earn drama; product surfaces earn clarity, restraint, and density control. Two common slop sources: brand drama applied to product UI, and timid product defaults applied to brand pages.
- Identify the category. Match the project to a row in the Category Design Guide below.
- Pick the tone. Use the category's recommended tone or choose a bold alternative -- never "modern and clean" (that is generic). Tone vocabulary to draw from: brutally minimal, maximalist, retro-futuristic, organic/natural, luxury/refined, playful/toy-like, editorial/magazine, brutalist/raw, art deco/geometric, industrial/utilitarian.
- Choose the theme from a scene, not a category. Dark vs. light is never a default. Write one sentence of physical scene -- who uses this, where, under what ambient light, in what mood -- and let it force the answer. "SRE glancing at incident severity at 2am in a dim room" forces dark; "the category is observability" forces nothing.
- Pick a color strategy (see Color Strategy below) before picking any hex values.
- State the memorable thing. What is the ONE element someone will remember? Commit to it.
- Vary across generations. If your last output was dark editorial, the next must differ -- unless the user explicitly requests consistency.
What ships with it
1 file beside SKILL.md 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.
- 12d ago First seen · 555 lines · 78 tokens per session scan A 8e160a1a7a63
anti-slop-design is a skill published in the GitHub repository madebyaris/advance-minimax-m3-cursor-rules (125 stars, last pushed 2mo ago), licensed MIT. It adds 78 tokens to every session and 8,345 once invoked, about $0.0004 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
design-review
Stress-test a plan or design against domain language, docs, and code. Ask hard questions one at a time. Update CONTEXT.md and ADRs as decisions crystallize. Use when you already have a draft plan or spec and want to find gaps before implementation.
motion-graphics
Use when the user wants a short, design-led motion graphic where motion is the message: kinetic typography, stat or number count-up, chart/data-viz hit, logo sting, brand lockup, lower-third, callout, social overlay, animated headline/tweet/news item, motion poster, or quick captured-page highlight. Usually under 10s…
visual-style
Create, extract, and apply portable visual design systems via visual-style.md files. Use when: (1) Creating a visual-style.md design system from scratch, (2) Extracting a visual style from a website URL, video, or PDF brand guide, (3) Applying a visual style to HeyGen videos, HTML slides, Figma, or paper.design, (4)…
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
design-system
Use this skill BEFORE writing or restyling ANY user-facing interface in WrongStack. It drives the Design Studio engine: commit to a kit, tune it (radius / density / font / motion), materialize the tokens into a real theme file, build against those tokens, then verify adherence. Trigger it whenever the user asks to…