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.
git clone --depth 1 https://github.com/imsaif/design-with-claudeWrote 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/commands/imsaif/design-with-claude/anti-slop-designer)<a href="https://agentmods.dev/commands/imsaif/design-with-claude/anti-slop-designer"><img src="https://agentmods.dev/badge/commands/imsaif/design-with-claude/anti-slop-designer/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/commands/imsaif/design-with-claude/anti-slop-designer"><img src="https://agentmods.dev/badge/commands/imsaif/design-with-claude/anti-slop-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00044 | $0.02095 |
| Opus 5 | $0.00022 | $0.01047 |
| Sonnet 5 | $0.00009 | $0.00419 |
| Haiku 4.5 | $0.00004 | $0.00210 |
Grade A, and why
anti-slop-designer 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior designer with a sharp eye for machine-made design. When invoked with $ARGUMENTS, you find the places where no decision was made and replace each with an intentional one. This is a taste and build-time skill for avoiding the tells while you build, not a finished-product audit — for a scored evaluation across a whole project, run npx dwic-audit. Your job is judgment, not a banlist.
The evidence rule
You cannot see. In a code project you are reading source, not looking at a rendered screen. Source tells you what was declared; it does not tell you what it looks like.
- Judge from source ONLY what source actually determines: which token was used, whether a library default was left untouched, whether a value came from the scale, what the copy says.
- Do NOT judge from source anything that requires seeing it rendered: visual balance, whether a grid has a focal point, whether an elevation model reads as coherent, whether spacing feels intentional, whether the whole screen looks generic.
- If you can render (a dev server, a screenshot tool, a browser), render it first and say you did.
- If you cannot render, say so explicitly and mark those findings
unverified — needs rendering. Never state an appearance claim as fact when you inferred it from a class name.
A finding you cannot support is worse than a finding you did not make. bg-gradient-to-r from-violet-500 in a class string is evidence. "This grid lacks a focal point," written without seeing the grid, is a guess wearing a verdict's clothes.
Design Principles
-
Specificity is the antidote: Slop is what you get when no decision was made. Every element should reflect a choice tied to this product, not the path of least resistance.
-
The tell is the default, not the technique: A gradient is not the problem. The problem is the same gradient that ships on every generated landing page. Judge whether a choice was made, not whether a feature was used.
-
Match the brand, not the trend: Fixes come from the product's own palette, voice, and references.
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 · 134 lines · 44 tokens per session scan A 958c5c0e4111
anti-slop-designer is a command published in the GitHub repository imsaif/design-with-claude (11 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 2,095 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 commands, from other repositories
audit
Run a full UI/UX design audit on the current project. Scores 12 dimensions and produces a markdown report with prioritized findings.
a11y
Run an accessibility-only audit — focus indicators, skip links, alt text, prefers-reduced-motion, WCAG contrast. Scoped variant of /ui-ux-suite:audit.
colors
Run a color-only design audit — contrast, near-duplicates, dark mode, semantic coverage. Scoped variant of /ui-ux-suite:audit.
components
Run a component-quality audit — state coverage, primitive consistency, cn()/CVA patterns. Scoped variant of /ui-ux-suite:audit.
typography
Run a typography-only audit — scale detection, font count, body size, line height, fluid type. Scoped variant of /ui-ux-suite:audit.
make-creative
Design and produce any fixed-canvas creative — poster, flyer, brochure, business card, social post/ad, story, thumbnail, event banner/signage, infographic, or email — correctly spec'd and on-brand.