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/seite-sh/seiteWrote 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/seite-sh/seite/design-prompts)<a href="https://agentmods.dev/rules/seite-sh/seite/design-prompts"><img src="https://agentmods.dev/badge/rules/seite-sh/seite/design-prompts/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/seite-sh/seite/design-prompts"><img src="https://agentmods.dev/badge/rules/seite-sh/seite/design-prompts.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 | $0.00000 | $0.00594 |
| Opus 5.5 | $0.00000 | $0.00238 |
| Sonnet 5.5 | $0.00000 | $0.00119 |
| Haiku 4.5 | $0.00000 | $0.00059 |
Grade A, and why
design-prompts 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 17d 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
Design Prompts
When asked to redesign or create a theme, use one of these directions as a starting point.
Edit templates/base.html directly — or apply a bundled theme first with seite theme apply <name> then edit.
Minimal / Editorial — Single column max 620px, Georgia serif body, geometric sans for UI elements.
No decorative elements. Bottom-border-only search input. White/off-white (#FAF9F6) background,
near-black (#1A1A1A) text, one muted link accent. Typography carries all personality.
Bold / Neo-Brutalist — Thick black borders (3px solid #000000), hard non-blurred box shadows
(6px 6px 0 #000). No border-radius. Saturated fill: yellow #FFE600, lime #AAFF00, or coral #FF4D00.
Cream (#FFFEF0) background. Font-weight 900. Headlines 4rem+. Buttons shift their shadow on hover to press in.
Bento / Card Grid — Responsive CSS grid, gap 16px, all cards border-radius 20px. Mixed card sizes
(1-, 2-, 3-col spans). Cards have independent background colors. Floating shadow:
box-shadow: 0 4px 24px rgba(0,0,0,0.08). Warm neutral palette (#F5F0EB) with one dark-accent card per row.
Dark / Expressive — True black (#000000 or #0A0A0A) surfaces. One neon accent:
green #00FF87, blue #0066FF, or violet #8B5CF6. Off-white text (#E8E8E8).
Translucent nav with backdrop-filter: blur(12px). Visible, styled focus rings.
Glass / Aurora — Gradient mesh background (violet #7B2FBE → teal #00C9A7, or
indigo #1A1040 → electric blue #4361EE). Floating panels: backdrop-filter: blur(16px),
rgba(255,255,255,0.10) fill, 1px solid rgba(255,255,255,0.2) border. Use for cards/nav only.
Accessible / High-Contrast — WCAG AAA ratios. Min 16px body. 3px colored focus rings
(design feature, not afterthought). Min 44px click targets. One semantic accent. No color-only
information. Full prefers-reduced-motion: reduce support.
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.
- 17d ago First seen · 35 lines · 0 tokens per session scan A bad707ae3d61
design-prompts is a cursor rule published in the GitHub repository seite-sh/seite (25 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 594 tokens. 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 2026-09-29.
Other cursor rules, from other repositories
frontend-architecture
Cursor rule "frontend-architecture" from tomasz-tomczyk/crit, covering frontend architecture, two-paradigm page fork, module pattern, shared modules (used by both modes) and code-review modules (used only by code-review mode).
proxy-auth-transport
Every CLI command or browser UI action that calls a crit-web API must work in both modes.
ui-assets
Docker staging for symlinked SPA and documentation assets.
design
All tasks related to updating frontend components, CSS, and general styling.
hatch3r-design-system-detection
Mandatory detection of existing design tokens, theme primitives, and component library before AI agents author new UI components.
hatch3r-ux-states-and-flows
Four-state surface contract (loading/empty/error/partial), user-flow decomposition before implementation, and microcopy + tone discipline for end-user UIs.