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 HECer/yoke --skill unslop-uigit clone --depth 1 https://github.com/HECer/yokeWrote 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/hecer/yoke/unslop-ui)<a href="https://agentmods.dev/skills/hecer/yoke/unslop-ui"><img src="https://agentmods.dev/badge/skills/hecer/yoke/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/hecer/yoke/unslop-ui"><img src="https://agentmods.dev/badge/skills/hecer/yoke/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 | $0.00070 | $0.00520 |
| Opus 5 | $0.00035 | $0.00260 |
| Sonnet 5 | $0.00014 | $0.00104 |
| Haiku 4.5 | $0.00007 | $0.00052 |
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 9d 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.
What it actually says
Un-slop the UI
AI-built UIs are "recognizable on sight" — a homogeneous look from a handful of default choices.
Before finishing UI work, remove these tells. Run yoke design-scan . for the statically
detectable ones, then apply judgement for the structural ones the scanner can't see.
The ranked tells (and the fix)
- AI-purple gradients (the #1 tell) — purple/violet gradients and
#6c5ce7-family accents. → Choose one real brand color with intent; avoid purple-by-default. - Gradient hero text —
bg-clip-text text-transparentrainbow headings. → Solid color + type weight/scale for emphasis. - Neon glow —
0 0 Npxcolored box-shadows /shadow-[0_0_...]. → Subtle, neutral elevation (small offset, low blur, low opacity). - Emoji-as-icons — 🚀✨🔥 in buttons/nav/feature lists. → A real icon set (lucide, etc.), consistent stroke + size.
- Untouched shadcn/Tailwind defaults — default radius, default slate everywhere. → Set deliberate tokens (radius, spacing scale, one accent) so it doesn't look boilerplate.
- Centered hero + three feature cards — the canonical AI landing layout. → Vary rhythm: asymmetry, a real product shot, content density that fits the product.
- Homogeneous spacing / no hierarchy — everything the same size and gap. → Establish a type scale and spacing rhythm; make the primary action obviously primary.
Rule
Treat yoke design-scan . as a gate (it exits non-zero over budget). Fix findings, then
eyeball the structural tells above. Distinctive, intentional > generic-but-safe.
Rubric informed by the MIT-licensed research in vibecoded-design-tells (© Carter Johnson). Yoke implements the idea natively; no code/data copied.
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.
- 9d ago First seen · 35 lines · 70 tokens per session scan A d3b2f65c20a7
unslop-ui is a skill published in the GitHub repository HECer/yoke (2 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 520 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
design-explore
Explore 2-4 design options with pros/cons/criteria matrix before writing code. Use for L3-L4 tasks (refactors, architecture, new subsystems). Pairs with savedecision MCP tool.
core-components
Core component library and design system patterns. Use when building UI, using design tokens, or working with the component library.
build-sdf-liquid-glass
Build lightweight SDF/canvas displacement glass with Vaso. Use for responsive refractive cards, no-WebGL fallbacks, many compact surfaces, or explicit SDF requests.
build-webgl-liquid-glass
Build production-ready GPU liquid-glass surfaces with liquid-gl for React or DOM UIs. Default for refractive cards, notifications, panels, GPU bevels, and WebGL glass.
wireframe
A template for an interactive React wireframe, a rough screen design used to plan an interface. It can show several screens, their transitions, and where data fields connect to the interface.
domain-model-diagram
A template for an interactive React domain model diagram, a visual map of the entities and relationships in a software system. It provides grid and focused views with pan, zoom, labels, and category colors.