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.
npx skills add seunghan91/ios26-design-system --skill ios26-designgit clone --depth 1 https://github.com/seunghan91/ios26-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/skills/seunghan91/ios26-design-system/ios26-design)<a href="https://agentmods.dev/skills/seunghan91/ios26-design-system/ios26-design"><img src="https://agentmods.dev/badge/skills/seunghan91/ios26-design-system/ios26-design/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/skills/seunghan91/ios26-design-system/ios26-design"><img src="https://agentmods.dev/badge/skills/seunghan91/ios26-design-system/ios26-design.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 | $0.00187 | $0.01919 |
| Opus 5.5 | $0.00075 | $0.00768 |
| Sonnet 5.5 | $0.00037 | $0.00384 |
| Haiku 4.5 | $0.00019 | $0.00192 |
Grade A, and why
ios26-design 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 2mo 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iOS 26 Design System
Build iOS 26 Liquid Glass interfaces on web and cross-platform. Source: Apple Figma Community Kit
Packages
npm install @ios26_design_system/tokens # CSS/JS/Dart tokens
npm install @ios26_design_system/svelte # Svelte 5
npm install @ios26_design_system/rails # Rails 8 + Hotwire
npm install @ios26_design_system/svelte-inertia # Svelte 5 + Inertia.js
npm install @ios26_design_system/metadata # 36 specs + 48 pages
Typography (SF Pro)
| Style | Size | Line Height | Weight | Spacing |
|---|---|---|---|---|
| Large Title | 34 | 41 | Regular/Bold | 0.4 |
| Title 1 | 28 | 34 | Regular/Bold | 0.38 |
| Title 2 | 22 | 28 | Regular/Bold | -0.26 |
| Title 3 | 20 | 25 | Regular/Semibold | -0.45 |
| Headline | 17 | 22 | Semibold | -0.43 |
| Body | 17 | 22 | Regular/Semibold | -0.43 |
| Callout | 16 | 21 | Regular/Semibold | -0.31 |
| Subheadline | 15 | 20 | Regular/Semibold | -0.23 |
| Footnote | 13 | 18 | Regular/Semibold | -0.08 |
| Caption 1 | 12 | 16 | Regular/Medium | 0 |
| Caption 2 | 11 | 13 | Regular/Semibold | 0.06 |
Font stack: "SF Pro", -apple-system, system-ui, sans-serif
Dynamic Type: 7 standard sizes (xSmall–xxxLarge) + 5 accessibility sizes (AX1–AX5) per style — never hardcode px. Weights: 9-step SF ramp (ultraLight 100 → black 900). SF Pro Text < 20pt, Display ≥ 20pt (auto).
Spacing (8pt grid)
Scale: 0=0, 1=4, 2=8, 3=12, 4=16, 5=20, 6=24, 8=32, 10=40
Inset: xs=8, sm=12, md=16, lg=20, xl=24, xxl=32
Margin: iPhone=16px, iPad=20px
Radius: none=0, xs=4, sm=8, md=10, lg=12, xl=16, xxl=20, full=9999
Liquid Glass
frostRadius: small=7px, medium=12px, large=14px
depth: 16, splay: 6, lightAngle: -45°
shadowBlur: layer=40px, background=80px
Light: large=#fafafa/0.7, medium=#f5f5f5/0.6
Dark: large=#000/0.8, medium=#000/0.6 (+tint #fff/0.06)
Pill: small=9999px, medium=20px, large=24px
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 127 lines · 187 tokens per session scan A c99de0c2b6dd
ios26-design is a skill published in the GitHub repository seunghan91/ios26-design-system (26 stars, last pushed 3mo ago), licensed MIT. It adds 187 tokens to every session and 1,919 once invoked, about $0.0007 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 2026-08-30.
ios26-design compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ios26-designseunghan91/ios26-design-system | Skill | 26 | 3mo ago | MIT | A | 187 | Claude Code, Codex |
| display-glasses-with-jetpack-compose-glimmerandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 112 | Claude Code |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| expo-design-systemexpo/skills | Skill | 4.1k | yesterday | MIT | A | 197 | Claude Code, Codex |
| flutter-build-responsive-layoutflutter/agent-plugins | Skill | 3.2k | 2d ago | BSD-3-Clause | A | 51 | Claude Code |
| omh-apple-designrlaope/oh-my-hermes | Skill | 5.2k | yesterday | MIT | A | 83 | Claude Code, Codex |
| axiom-audit-liquid-glassCharlesWiltgen/Axiom | Skill | 1.3k | yesterday | MIT | A | 32 | Codex |