anti-slop is a set of rules and skills that coding agents use to avoid generic AI-generated interfaces, copy, and code. It is intended for people building pages or writing and reviewing text with an agent, while a user-provided DESIGN.md supplies the visual direction. The catalogue entries package these rules as agent skills and a plugin.
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 miqdadbadjuber/anti-slop --skill antislop-uigit clone --depth 1 https://github.com/miqdadbadjuber/anti-slopWrote 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/miqdadbadjuber/anti-slop/antislop-ui)<a href="https://agentmods.dev/skills/miqdadbadjuber/anti-slop/antislop-ui"><img src="https://agentmods.dev/badge/skills/miqdadbadjuber/anti-slop/antislop-ui/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/miqdadbadjuber/anti-slop/antislop-ui"><img src="https://agentmods.dev/badge/skills/miqdadbadjuber/anti-slop/antislop-ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- 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 | $0.00035 | $0.05794 |
| Opus 5 | $0.00017 | $0.02897 |
| Sonnet 5 | $0.00007 | $0.01159 |
| Haiku 4.5 | $0.00003 | $0.00579 |
Grade A, and why
antislop-ui 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
antislop-ui
Anti Slop: Rules for AI Coding Agents. UI & Visual skill
Part of the antislop system. Read together with
antislop.md(the core). This skill deep-dives the UI/visual concern: color, layout, components, decoration, structural flow, and motion. It references core rules by number and never duplicates or renumbers them. Load it when the task builds or edits a website, web app, or any interface.
How to use this skill
- Load together with
antislop.mdwhenever the task is UI or visual work. The core holds the mechanism (the purpose test, the three tiers, the Delivery Gate); this skill holds UI-specific depth. - Every entry has the same shape: Tell (the pattern), Why (why it reads as slop), Fix (what to do instead), with the governing core rule cited as R-XX.
- The Delivery Gate in the core remains the gate. The "UI Skill Checklist" at the end of this file is the UI-specific supplement to run alongside it.
Visual & Color
Generic Blue-Purple Gradient
- Tell: blue-to-purple, blue-to-cyan, or purple-to-pink gradients used as the primary color treatment, or a full-page colored glow.
- Why: the most over-represented color treatment in training data. It signals "no brand identity", not "our palette", and marks the design as AI-generated at a glance.
- Fix: pull the palette from
DESIGN.mdor the product's own identity. Keep a gradient only as a hierarchy function with the reason written down (R-01). A gradient separating one level from another is craft; the same gradient on every section is a default. - The same default family: harsh or rainbow gradients, purple-and-black schemes, neon or pastel palettes, and blurred radial orbs behind the hero. They are the same tell wearing different clothes: color from the model's default, not from the brand. All of them are FORBIDDEN as defaults without purpose (R-01).
Excessive Glassmorphism
- Tell: blur/backdrop-filter on the navbar, cards, modals, and sidebar at the same time.
- Why: blur removes texture and sits every surface in the same frosted layer, flattening hierarchy. When every surface is glass, nothing is foreground.
- Fix: treat glass as an accent, not a character trait. Dose cap: at most 1-2 elements (R-10). The surface that needs the attention gets the glass; everything else stays solid.
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 · 298 lines · 35 tokens per session scan A 3ca13ea8c324
antislop-ui is a skill published in the GitHub repository miqdadbadjuber/anti-slop (2,046 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 5,794 once invoked, about $0.0002 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
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.