A command for reviewing a frontend for common signs of generic, AI-generated design and rewriting the affected parts.

Scanning gradients, colors, layouts, typography, and visual effects, then reporting each issue with its file and line location for targeted changes.

It helps identify repetitive layouts, default colors, overused effects, weak typography choices, and other patterns that make interfaces feel interchangeable.

anti-slop — Command for Claude Code by Muminur

Install

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.

Clone the repo

git clone --depth 1 https://github.com/Muminur/frontend-design-craft-skill

Made for: Claude Code.

Or install craft, the plugin that ships this one along with the rest of its 4 skills, 13 commands.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/muminur/frontend-design-craft-skill/anti-slop/github.svg)](https://agentmods.dev/commands/muminur/frontend-design-craft-skill/anti-slop)

Your own site

<a href="https://agentmods.dev/commands/muminur/frontend-design-craft-skill/anti-slop"><img src="https://agentmods.dev/badge/commands/muminur/frontend-design-craft-skill/anti-slop/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/muminur/frontend-design-craft-skill/anti-slop"><img src="https://agentmods.dev/badge/commands/muminur/frontend-design-craft-skill/anti-slop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 750 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00012	$0.00750
Opus 5	$0.00006	$0.00375
Sonnet 5	$0.00002	$0.00150
Haiku 4.5	$0.00001	$0.00075

Measured 10d ago against content hash 6fcbee647757, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

anti-slop 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 10d 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.

commands/anti-slop.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/anti-slop

Scan the target for AI-generated tells and rewrite them. This is the focused, surgical version of /polish for the taste lens specifically.

Target

$ARGUMENTS

The scan

Run through this checklist and report each hit with file:line:

Gradients & color

Purple → blue, pink → orange, teal → blue gradient on hero
Gradient text
#000 pure black on #FFF pure white
Default Tailwind blue-* / purple-* as primary brand
More than one gradient moment per page

Layout

Centered hero: stacked headline + subhead + 2 CTAs + image below
Three equal columns, icon-title-blurb feature pattern
Equal-width logo cloud with generic startup names
3-tier pricing with middle tier highlighted "Most popular"
Bento grid where every cell is the same radius and shadow
FAQ accordion bolted to the bottom of every page

Typography

Inter loaded without justification
All sections centered without a structural reason
Heading and body using the same line-height
No tracking adjustment on display sizes
Default sentence case everywhere, no rhythm of cases

Visual effects

Glassmorphism / backdrop-filter: blur cards
Neon glows on buttons or text
Soft drop shadows on most elements
Default shadcn/ui theme unmodified
Heroicons / Lucide used unchanged

Content

Lorem ipsum
John Doe, Jane Smith, Acme, Example Co
Fake stats: "99.9% uptime", "10x faster", "Trusted by 10,000+ teams" without source
Generic testimonials with first name + "CEO"
Unsplash hero photos (laptops, sunsets, cities, hands on keyboards)
Stock illustrations from unDraw / Storyset mashed together

The rewrite

For each hit, propose a specific replacement. Do not just say "remove" — say what it becomes.

Examples (these are patterns, not commands):

Centered hero → asymmetric 7/5 split with headline left, real product visual right
Inter → archetype-appropriate sans (Geist, General Sans, Cabinet Grotesk, IBM Plex)
Purple-blue gradient → solid brand color in OKLCH, used sparingly
Lorem ipsum → write actual copy that fits the product
John Doe → ask user for real names, or use varied realistic placeholders
Three-column feature grid → rearrange as a single hero feature + supporting list, or 2x2 asymmetric

Read the full file on GitHub · 88 lines

Changes

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.

10d ago First seen · 88 lines · 12 tokens per session scan A 6fcbee647757

Subscribe to this mod's changes

anti-slop is a command published in the GitHub repository Muminur/frontend-design-craft-skill (4 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 750 once invoked, about $0.0001 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 2026-08-31.

CSS and styling Design and UX Frontend

ux-recommend

The v2 flagship. Runs the 5-parallel-search Python engine across 11 data manifests (75+ styles, 170+ palettes, 65+ type pairs, 120+ components, 170+ industries, 110+ UX laws, 50+ motion presets, 120+ anti-patterns, 92 brand specs) and returns a complete recommended design system for your project — with always-on…

Laith0003/ux-skill · 93 tokens

anti-slop