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 the-hooman-loop/anti-slop-kit --skill deslop-designgit clone --depth 1 https://github.com/the-hooman-loop/anti-slop-kitWrote 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/the-hooman-loop/anti-slop-kit/deslop-design)<a href="https://agentmods.dev/skills/the-hooman-loop/anti-slop-kit/deslop-design"><img src="https://agentmods.dev/badge/skills/the-hooman-loop/anti-slop-kit/deslop-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/the-hooman-loop/anti-slop-kit/deslop-design"><img src="https://agentmods.dev/badge/skills/the-hooman-loop/anti-slop-kit/deslop-design.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 | $0.00070 | $0.00713 |
| Opus 5 | $0.00035 | $0.00357 |
| Sonnet 5 | $0.00014 | $0.00143 |
| Haiku 4.5 | $0.00007 | $0.00071 |
Grade A, and why
deslop-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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deslop design
AI slop is ugly in a specific way: it piles on every possible style at once — a gradient, a glow, a mascot, emoji, a wall of glowing cards, every default switched on — until every product looks like the same template. It reads as "designed" in a thumbnail and falls apart on a second look. Strip it back to something a person would actually choose.
Principles
- Decide before you decorate. Every visual choice must be explainable.
- One accent, one voice. A single accent color and a consistent tone; not a rainbow.
- Hierarchy from scale and space. Size, weight, and whitespace carry hierarchy. Coloring words or swapping fonts is a shortcut, not a system.
- Subtract first. The first move toward not-ugly is removing things.
- Specific beats punchy in copy. Concrete labels over slogans.
- Decoration must mean something. Icons, badges, and callouts are signals, not filler.
Reject the default AI looks
Do not reach for these unless the brief explicitly asks for them. AI design converges on a handful of defaults; naming them helps you avoid them:
- Warm cream background (near
#F4F1EA) + high-contrast serif display + terracotta accent. - Near-black background + a single acid-green or vermilion accent.
- Broadsheet layout with hairline rules, zero radius, dense newspaper columns.
- Purple/indigo gradient heroes, soft drop shadows, rounded cards,
Intereverywhere. - Emoji as section markers; glow effects; a floating gradient blob background.
The slop fingerprint shifts over time. Target the convergence mechanism (picking the statistical median) rather than a frozen blocklist.
Strategy drives design
Commit to words before pixels: what this is, who it serves, and the adjectives it must feel like. Translate those words into a type and color system, build from tokens, then apply the craft layer (layout, components, motion, accessibility), then audit. Never pick aesthetics first. A beautiful look that fights the artifact's job is its own slop — a dashboard, a portfolio, and a checkout share almost no design DNA.
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 · 61 lines · 70 tokens per session scan A 5aba98855dcb
deslop-design is a skill published in the GitHub repository the-hooman-loop/anti-slop-kit (4 stars, last pushed 18d ago), licensed MIT. It adds 70 tokens to every session and 713 once invoked, about $0.0003 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.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.