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 randommonicle/claude-skills --skill unslop-uigit clone --depth 1 https://github.com/randommonicle/claude-skillsWrote 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/randommonicle/claude-skills/unslop-ui)<a href="https://agentmods.dev/skills/randommonicle/claude-skills/unslop-ui"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/unslop-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/randommonicle/claude-skills/unslop-ui"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/unslop-ui.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 | $0.00209 | $0.01849 |
| Opus 5 | $0.00105 | $0.00924 |
| Sonnet 5 | $0.00042 | $0.00370 |
| Haiku 4.5 | $0.00021 | $0.00185 |
Grade A, and why
unslop-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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
unslop-ui
Read this first, because the most common misunderstanding sinks the whole thing.
This skill does not give you a good design, and it does not have a preferred look. It does two narrow things. It removes the specific cues that make a site read as AI-generated, and it forces a deliberate, project-specific choice where the model would otherwise reach for its default. Taste, brand, and layout judgment are still yours. A guardrail is not a designer.
The trap to avoid (this is the whole point)
The failure mode of every anti-slop effort is replacing one default look with another. The 2024 tell was the purple-to-blue gradient on a dark hero. The 2026 tell is a warm cream background with a serif display font (Instrument Serif, Fraunces) and a sage or forest green accent, which is the current Claude/Anthropic house style. Swapping the first for the second is not unslopping. It just resets the clock, and people clock it just as fast.
So this skill never prescribes a palette, a font, or a layout. Prescribing one is how you become next year's slop. What it does instead: detect the defaults (old AND new), and require that any replacement be a specific choice the user or project actually made, not the model's next-most-likely guess. The only universal rule here is "make a deliberate choice and be able to say why," which is the one thing a default never is.
If the user genuinely wants purple, neon, a serif, or a cream background as a real brand
decision, that is not slop and the skill leaves it alone. A tell is an unspecified
default, not a banned color. Honor unslop-ignore (see Audit mode) for anything chosen
on purpose.
How this differs from the built-in frontend-design skill
Claude already ships a frontend-design skill, and it is good, but it produces the cream
- serif + green house look that this skill now flags as a tell. unslop-ui is complementary and adds three things that one does not: a deterministic scanner you can run in CI (exit code gates a build), a data-grounded ranking so effort goes where real complaints are, and an explicit check against the new "tasteful default" so you do not launder slop into a different slop. Use both. Let the design skill build; let this one keep it honest.
What ships with it
9 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.
- 12d ago First seen · 136 lines · 209 tokens per session scan A 98800da54e8e
unslop-ui is a skill published in the GitHub repository randommonicle/claude-skills (23 stars, last pushed 5d ago), licensed Apache-2.0. It adds 209 tokens to every session and 1,849 once invoked, about $0.0010 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.