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/Eldergenix/SUPER-DESIGNWrote 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/eldergenix/super-design/cursor-rule)<a href="https://agentmods.dev/rules/eldergenix/super-design/cursor-rule"><img src="https://agentmods.dev/badge/rules/eldergenix/super-design/cursor-rule/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/eldergenix/super-design/cursor-rule"><img src="https://agentmods.dev/badge/rules/eldergenix/super-design/cursor-rule.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 | $0.00528 | $0.00528 |
| Opus 5.5 | $0.00211 | $0.00211 |
| Sonnet 5.5 | $0.00106 | $0.00106 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
cursor-rule 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 1mo 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 System Rules
Read DESIGN.md at the project root before any UI work. It is the closed token layer — every color, spacing, typography, radius, shadow, and animation value in component code MUST reference a token defined there.
Hard rules
- No hardcoded values in component code — no
#hex, norgb(), nohsl(), no unscaledpx. Reference a token. - Every interactive element defines
hover,focus-visible,active,disabled. Buttons addloading. Inputs adderror,readonly. - Use
:focus-visiblefor keyboard focus rings. 3px outline, 2px offset, 3:1 contrast. - Animate only
transformandopacity. Neverwidth/height/top/left/margin/padding. - Respect
prefers-reduced-motion. Replace movement with opacity changes. - Max 300 LOC per component file. Extract when JSX nests > 4 levels deep.
- Min 44×44 touch targets. 8px minimum gap.
- Responsive at 320/375/768/1024/1440/1920. Container queries for reusable components, media queries for page shells.
Reference
Full skill and framework adapters live at .claude/skills/super-design/. Load on demand:
references/tokens-schema.md— DTCG token formatreferences/state-matrix.md— required states per component + ARIAreferences/animation-tokens.md— durations / easings / recipesreferences/responsive-patterns.md— breakpoints / clamp / container queriesreferences/component-quality-gates.md— LOC / complexity / scoringreferences/screenshot-to-code-workflow.md— 7-pass extraction loopreferences/framework-adapters/{tailwind-v4,tailwind-v3,shadcn,mui,radix,geist}.md
Self-check before declaring done
Run bash .claude/skills/super-design/scripts/quality-score.sh <file>. Target ≥ 90 (grade A).
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.
- 1mo ago First seen · 37 lines · 528 tokens per session scan A f3d32c67382c
cursor-rule is a cursor rule published in the GitHub repository Eldergenix/SUPER-DESIGN (3 stars, last pushed 1mo ago), licensed MIT. It adds 528 tokens to every session, about $0.0021 per session on Opus 5.5. 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
ux-expert
This rule is triggered when the user types @ux-expert and activates the UX Expert agent persona.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.