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 agentmods add skills/fusengine/agents/design-iosnpx skills add fusengine/agents --skill design-iosgit clone --depth 1 https://github.com/fusengine/agentsWrote 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/fusengine/agents/design-ios)<a href="https://agentmods.dev/skills/fusengine/agents/design-ios"><img src="https://agentmods.dev/badge/skills/fusengine/agents/design-ios.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.01974 |
| Opus 5 | $0.00018 | $0.00987 |
| Sonnet 5 | $0.00007 | $0.00395 |
| Haiku 4.5 | $0.00004 | $0.00197 |
Grade A, and why
design-ios 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 yesterday.
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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The deliverable is a device-framed (iOS) or window-framed (macOS) HTML mockup at exact viewport dimensions plus a SwiftUI-ready handoff spec (named tokens, text styles, semantic colors, sizing, states, spacing). This skill never writes SwiftUI code — implementation is left to swift-expert or an Apple-platform developer.
Design iOS/macOS — Mockup and Handoff, Not Code
When
After design-system tokens exist. This skill never writes SwiftUI — it produces a
static HTML mockup at exact device/window dimensions plus a spec that swift-expert or
an Apple-platform developer implements.
Input
design-system.md— OKLCH palette, typography direction, motion personality.- The screen/flow to mock up and the target platform: iPhone / iPad (iOS) or a resizable window (macOS).
Steps — iOS
- Map tokens to iOS roles. Typography → Dynamic Type text styles, anchored at Body
17pt down to Caption 2 11pt (never fixed point sizes) — see
references/dynamic-type.md. Colors → semantic color roles (never raw RGB/hex) — seereferences/semantic-colors.md. - Pick the device viewport(s) from
references/viewports.md— mock up in exact points at the chosen scale factor. - Build the HTML mockup: a device-frame
<div>at the exact viewport dimensions,viewport-fit=covermeta tag,env(safe-area-inset-*)for notch/Dynamic Island/home indicator spacing. Seereferences/mockup.md. - Apply Liquid Glass where it fits — a floating layer of controls above regular
content, not a content background. Two variants: regular (content-aware, the
default for controls) and clear (more transparent — dim the content beneath it
~35% when clear sits over light content, so controls stay legible). Plus control
morphing, concentricity between nested shapes, layered icon treatment. Source:
developer.apple.com/design/human-interface-guidelines/materials (Liquid Glass, iOS 26).
See
references/liquid-glass.md— do not invent numeric corner-radius values; none are published. - Verify touch targets and contrast: 44×44pt minimum touch target (see
references/touch-targets.md); 4.5:1 minimum contrast in Dark Mode for body text (WCAG AA, HIG-endorsed) — check both light and dark againstreferences/semantic-colors.mdroles, not a single-mode check. - Sidebar navigation ≤ 2 levels deep. If the flow needs a 3rd level, restructure (tabs, push navigation, or a secondary sidebar) rather than nesting a 3rd disclosure tier — deeper sidebars are a documented HIG anti-pattern for iPadOS/macOS sidebars. Source: developer.apple.com/design/human-interface-guidelines/layout.
- Write the handoff spec per
references/handoff-swiftui.md: named tokens only (never raw values), Dynamic Type text styles (never fixed sizes), semantic colors, explicit sizing behavior (fixed/hug/fill) per element, all interaction states (disabled/pressed/focused), spacing in pt.
What ships with it
7 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.
- yesterday First seen · 121 lines · 37 tokens per session scan A 4c752117beef
design-ios is a skill published in the GitHub repository fusengine/agents (25 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 1,974 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
app-store-optimization
Improves visibility and conversion in the App Store and Google Play — metadata, keywords, screenshots, ratings, and the listing experience that turns an impression into an install. Use this to audit or optimize an app listing, plan a launch listing, diagnose poor install conversion, or improve store search visibility.
bootstrap-xcode-workspace
Create, adopt, extend, and align one Swift product workspace with app, extension, package, and service components under one permanent Xcode entrypoint.
release-readiness-workflow
Check Android release readiness without publishing by default, including versionCode and versionName, signing and keystore boundaries, release build types, R8/ProGuard, mapping outputs, app bundles, APKs, Play delivery handoffs, privacy, permissions, changelogs, and repository-owned release automation routing through…
testing-lint-workflow
Plan, run, filter, and triage Android tests and lint, including local unit tests, instrumentation and Compose UI test handoffs, Gradle variant tasks, lint configuration, lint baselines, failure explanations, emulator-aware validation routing, and readable next checks.
radin-record
Log feedback, bugs, follow-ups, or ideas raised mid-session as structured backlog entries, so they survive past the conversation. Use for /radin-record, "log this to the backlog", "add as follow-up/bug/idea", "record what we just found", "note this for later", "add findings to backlog". Triggers even on vague asks…
swiftui-app-architecture-workflow
Guide SwiftUI app-structure decisions for Apple apps across App, scenes, commands, focus, environment, preferences, window and document coordination, and reusable view composition. Use when the user wants help deciding where ownership belongs in a SwiftUI app, which data-flow mechanism fits a responsibility, or how to…