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 | $0.00039 | $0.06804 |
| Opus 5.5 | $0.00016 | $0.02722 |
| Sonnet 5.5 | $0.00008 | $0.01361 |
| Haiku 4.5 | $0.00004 | $0.00680 |
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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- antislop-ui — 91% identical, 35 lines differ
How it starts
The opening of the file, as written. The whole thing — 345 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 ships with it
3 files 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.
- yesterday Changed · +33 lines · +4 tokens per session e8cb54f3d436
- 1mo ago Changed · +7 lines 47d989277125
- 1mo ago Changed · +7 lines ad02d49de301
- 2mo 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 (7,562 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 6,804 once invoked, about $0.0002 per session on Opus 5.5. 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
role-ui-ux-designer
Use when orchestrating UI/UX design systems, anti-AI-slop frontend styling, tactile micro-interactions, responsive design tokens, accessibility standards, and high-fidelity interface engineering.
taste
Anti-slop frontend engineering directive and design taste system. Enforces brief inference, dynamic design dials, absolute prohibition of AI visual tells, and 100% full-output completion.
design-system-patterns
Token architecture, component design, naming conventions, theming, and scaling design systems that people actually use.
accessibility-deep-patterns
Advanced accessibility patterns including ARIA, screen reader optimization, cognitive accessibility, and motor impairment design.
animation-choreography
Page transition choreography, staggered animations, and orchestrated motion sequences.
border-craft
Border design patterns, dividers, separators, and using borders as primary design elements.