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/Kevin-Liu-01/Sigil-UIWrote 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/rules/kevin-liu-01/sigil-ui/taste-enforcement)<a href="https://agentmods.dev/rules/kevin-liu-01/sigil-ui/taste-enforcement"><img src="https://agentmods.dev/badge/rules/kevin-liu-01/sigil-ui/taste-enforcement/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/rules/kevin-liu-01/sigil-ui/taste-enforcement"><img src="https://agentmods.dev/badge/rules/kevin-liu-01/sigil-ui/taste-enforcement.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 | $0.02171 | $0.02171 |
| Opus 5 | $0.01086 | $0.01086 |
| Sonnet 5 | $0.00434 | $0.00434 |
| Haiku 4.5 | $0.00217 | $0.00217 |
Grade A, and why
taste-enforcement 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.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taste Enforcement — Anti-Slop Frontend Rules
Adapted from tasteskill.dev for Sigil's token-driven architecture. These rules override default LLM biases that produce generic, forgettable frontends. Cross-reference with
sigil-design-system.mdcfor token consumption rules.Available taste skills (user-level at
~/.cursor/skills/taste-*/SKILL.md):
taste-core— general anti-slop defaulttaste-gpt— GPT/Codex stricter varianttaste-image-to-code— image-first then implementtaste-redesign— audit existing UItaste-soft— premium calm/expensivetaste-output— output completenesstaste-minimalist— editorial monochrometaste-brutalist— Swiss/CRT/terminaltaste-stitch— Google Stitch DESIGN.mdtaste-imagegen-web— web reference imagestaste-imagegen-mobile— mobile screen imagestaste-brandkit— brand-kit overview imagesSee taste-skills-index.mdc for the full selection guide.
Variance Baseline
These dials drive all downstream decisions. Adjust per-prompt when the user specifies a different mood.
| Dial | Default | Range | What It Controls |
|---|---|---|---|
| DESIGN_VARIANCE | 8 | 1-10 | Layout asymmetry, grid complexity, whitespace distribution |
| MOTION_INTENSITY | 6 | 1-10 | Animation density, spring physics, scroll effects |
| VISUAL_DENSITY | 4 | 1-10 | Spacing tightness, card usage, data presentation |
Interpret user requests dynamically: "make it airy" → VISUAL_DENSITY 2; "dashboard" → VISUAL_DENSITY 7-8; "cinematic" → MOTION_INTENSITY 8-9.
Banned Visual Patterns (Hard Failures)
These patterns are the hallmark of generic AI output. Never produce them.
Layout
- Centered hero + blur blobs when DESIGN_VARIANCE > 4. Use split-screen, left-aligned, or asymmetric whitespace.
- 3 equal cards in a row for feature sections. Use 2-column zig-zag, asymmetric bento, or horizontal scroll.
h-screenfor full-height sections. Always usemin-h-[100dvh].- Flexbox percentage math (
w-[calc(33%-1rem)]). Use CSS Grid. - Complex layouts without mobile fallback. Levels 4-10 variance MUST collapse to single-column below
md:.
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 · 155 lines · 2,171 tokens per session scan A ef94fbe9f906
taste-enforcement is a cursor rule published in the GitHub repository Kevin-Liu-01/Sigil-UI (9 stars, last pushed 1mo ago), licensed MIT. It adds 2,171 tokens to every session, about $0.0109 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 cursor rules, from other repositories
external-scale
Source: docs/agents/external-scale.md Regenerate: npm run agents:sync -w packages/openbridge-webcomponents -->.
building-blocks
Source: docs/agents/building-blocks.md Regenerate: npm run agents:sync -w packages/openbridge-webcomponents -->.
sheleg-design
Apply SHELEG Design when building a cinematic scroll-driven landing page, hero, or particle/WebGL scroll experience — or when styling product UI (dashboards, admin, internal tools) with its style packs.
frontend
React/Next.js frontend coding standards with shadcn/ui, Tailwind CSS v4, and FSD-lite architecture.
tinted-ui-tokens-skills
Generate a brand-tinted UI design-token system (CSS) from a single brand color. No pure neutral colors.
design
Design system, typography, color, accessibility (WCAG 2.2), responsive-first layout, and motion design standards.