Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Kevin-Liu-01/Sigil-UInpx agentmods add rules/kevin-liu-01/sigil-ui/sigil-design-systemWrote 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/sigil-design-system)<a href="https://agentmods.dev/rules/kevin-liu-01/sigil-ui/sigil-design-system"><img src="https://agentmods.dev/badge/rules/kevin-liu-01/sigil-ui/sigil-design-system/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/sigil-design-system"><img src="https://agentmods.dev/badge/rules/kevin-liu-01/sigil-ui/sigil-design-system.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 | $0.05196 | $0.05196 |
| Opus 5 | $0.02598 | $0.02598 |
| Sonnet 5 | $0.01039 | $0.01039 |
| Haiku 4.5 | $0.00520 | $0.00520 |
Grade A, and why
sigil-design-system 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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sigil Design System — Enforced Rules
Imported from Kevin's wiki and the Dedalus design language. These rules are non-negotiable when writing or reviewing Sigil code.
Full references: style/design.md (motion guide) | style/ux-principles.md (product UX) | style/style.md (engineering philosophy) | skills/sigil-polish/ (interface polish skill with typography, surfaces, animations, performance deep-dives)
Anti-slop enforcement: Also read taste-enforcement.mdc for banned AI visual patterns, variance dials, content quality rules, performance guardrails, and output completeness requirements. The taste-skills-index.mdc catalogs the 12 user-level taste skills (taste-core, taste-soft, taste-minimalist, taste-brutalist, etc.) that auto-trigger based on task description.
Companion rule files (imported from wiki):
- css-ui-enforcement.mdc — Tailwind +
cn()first,globals.cssonly, scrollbars, hit areas, nostyle+classNamesoup- react-conventions.mdc — Hooks, linting (Ultracite/oxlint), architecture-policy ESLint rules, Vercel 69 rules, RSC safety
- typescript-conventions.mdc — Types, error handling (
Result<T,E>, Zod), console labels, tsgo, oxfmt- design-animation-rules.mdc — Animation frequency framework, easing flowchart, springs, clip-path, gestures, accessibility, Sonner principles
- frontier-stack.mdc — Default animation/3D/rendering stack, decision matrix, json-render for generative UI
- dashboard-design.mdc — Dashboard design system (14px base, stat cards, charts, sidebar, empty states, 6-rule cheatsheet)
- interface-micro-polish.mdc — Dark 1px card shadow, image outlines, icon animation, staggered enters, softer exits
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 · 327 lines · 5,196 tokens per session scan A a6739d7acb8d
sigil-design-system is a cursor rule published in the GitHub repository Kevin-Liu-01/Sigil-UI (9 stars, last pushed 1mo ago), licensed MIT. It adds 5,196 tokens to every session, about $0.0260 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.