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/opensquad-ai/opensquadWrote 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/opensquad-ai/opensquad/opensquad-ui)<a href="https://agentmods.dev/rules/opensquad-ai/opensquad/opensquad-ui"><img src="https://agentmods.dev/badge/rules/opensquad-ai/opensquad/opensquad-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/rules/opensquad-ai/opensquad/opensquad-ui"><img src="https://agentmods.dev/badge/rules/opensquad-ai/opensquad/opensquad-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 | $0.00000 | $0.00403 |
| Opus 5.5 | $0.00000 | $0.00161 |
| Sonnet 5.5 | $0.00000 | $0.00081 |
| Haiku 4.5 | $0.00000 | $0.00040 |
Grade A, and why
opensquad-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 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
OpenSquad UI (soft tooling)
Read DESIGN.md for full tokens. Follow this when changing frontend chrome.
Skill combo (do not load all remote skills every time)
- Anthropic frontend-design — brief before big UI changes
- Impeccable quieter / polish — softer spacing, type, motion
- garden
linear— hairline panels, radius ≤16, one muted accent - qiaomu — Chinese copy / 盘古之白 only when editing zh strings
- Pro Max / Taste — not for routine app chrome (landing only for Taste)
Hard rules
- Use semantic Tailwind colors (
bg-bgLight,bg-panel,border-border,text-textMain,text-textMuted,primary). No hardcoded purple/indigo brand gradients. - Theme colors only via
themeStore/themeEngineCSS vars. - Radius: 6 / 12 / 16 max for chrome. Soft single-layer shadow; prefer hairline borders.
- Motion 150–200ms ease-out; honor
prefers-reduced-motion. - Modal headers: quiet panel + border — not full-bleed primary bars.
- Nav active: soft primary tint, not loud filled blocks.
- Ban: emoji-as-icons, glow shadows, multi-accent rainbow, AI landing-page clichés in product UI.
Soft pass checklist
Before finishing a UI change: quieter contrast, consistent 8px spacing rhythm, focus rings via ring-primary/25, light + dark both readable.
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 · 34 lines · 0 tokens per session scan A 9309f1056e9a
opensquad-ui is a cursor rule published in the GitHub repository opensquad-ai/opensquad (7 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 403 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 2026-08-31.
Other cursor rules, from other repositories
ui-styling
A set of rules for writing user-interface styles, including when to use shadcn defaults and when to move long class lists into a `.styles.ts` file.
ux
Use when working on UI/UX tasks, user experience design, interface components, and user journey optimization - provides comprehensive UX workflow with design systems integration.
design
All tasks related to updating frontend components, CSS, and general styling.
front-end-rule
Use HTML imports with Bun.serve(). Don't use vite. HTML imports fully support React, CSS, Tailwind.
color-tokens
A rule set for choosing interface colors through shared semantic design tokens. These tokens are named meanings such as primary, success, notice, or destructive rather than fixed color values.
frontend-theme-guidelines
Frontend theme-system rules for NekroAgent, covering the theme architecture, core file structure, design principles, and usage guidance. A theme system controls shared visual choices such as colors, typography, and layouts.