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 memi-design/design-skills --skill swiftui-design-engineeringgit clone --depth 1 https://github.com/memi-design/design-skillsWrote 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/memi-design/design-skills/swiftui-design-engineering)<a href="https://agentmods.dev/skills/memi-design/design-skills/swiftui-design-engineering"><img src="https://agentmods.dev/badge/skills/memi-design/design-skills/swiftui-design-engineering/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/memi-design/design-skills/swiftui-design-engineering"><img src="https://agentmods.dev/badge/skills/memi-design/design-skills/swiftui-design-engineering.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 | $0.00037 | $0.00512 |
| Opus 5.5 | $0.00015 | $0.00205 |
| Sonnet 5.5 | $0.00007 | $0.00102 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
swiftui-design-engineering 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SwiftUI Design Engineering
Use this workflow when the deliverable is SwiftUI source, an iOS screen specification, or a review of an existing Apple-platform interface.
Workflow
- Inspect the project before choosing APIs: deployment targets, Swift language mode, nearby views, navigation ownership, dependency injection, test targets, and asset/token conventions.
- Write the screen contract first: user goal, states, navigation, data ownership, platform availability, Dynamic Type behavior, VoiceOver order, reduced-motion behavior, and acceptance checks.
- Reuse local components and semantic assets. Do not invent parallel button, card, spacing, color, or typography systems.
- Keep state at the narrowest owner. Prefer value state for local UI, explicit inputs for feature dependencies, and environment injection only for genuinely shared services.
- Compose small views around stable identities. Keep networking, persistence, formatting, and routing out of expensive
bodypaths. - Add previews or fixtures for loading, empty, populated, error, large text, dark appearance, and right-to-left layout when relevant.
- Build and test the smallest target, then run the critical simulator flow. Record commands and outcomes in the handoff.
Design contract
- Use semantic system colors and asset catalog names, not raw repeated literals.
- Treat Dynamic Type, safe areas, keyboard avoidance, localization, and orientation as layout inputs.
- Use native controls before custom gestures. Preserve standard navigation, focus, selection, and dismissal behavior.
- Give every interactive control an accessible name and at least a 44 by 44 point practical hit region.
- Gate newer APIs with explicit availability and a behaviorally equivalent fallback.
- Do not claim a preview, build, test, or simulator flow passed unless it ran.
Load on demand
Read references/verification.md for the state matrix, source organization, and verification receipt.
Route custom Shader, colorEffect, distortionEffect, layerEffect, Metal, dithering, or GPU-effect work through shader-design-engineering. Use creative-rendering-audit when the outcome is a scored, evidence-backed rendering review.
What ships with it
2 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 · 36 lines · 37 tokens per session scan A a1a568a24797
swiftui-design-engineering is a skill published in the GitHub repository memi-design/design-skills (7 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 512 once invoked, about $0.0001 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 2026-09-03.
swiftui-design-engineering compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| swiftui-design-engineeringmemi-design/design-skills | Skill | 7 | 1mo ago | MIT | A | 37 | Claude Code, Codex |
| swiftui-native-firsttroyjthomas/ios-agent-skills | Skill | 2 | 5mo ago | MIT | A | 65 | Claude Code, Codex |
| uikit-bridgingtroyjthomas/ios-agent-skills | Skill | 2 | 5mo ago | MIT | A | 70 | Claude Code, Codex |
| dark-mode-legibilitytroyjthomas/ios-agent-skills | Skill | 2 | 5mo ago | MIT | A | 84 | Claude Code, Codex |
| pixel-and-stroke-geometrytroyjthomas/ios-agent-skills | Skill | 2 | 5mo ago | MIT | A | 104 | Claude Code, Codex |
| polish-and-refinementtroyjthomas/ios-agent-skills | Skill | 2 | 5mo ago | MIT | A | 80 | Claude Code, Codex |
| app-store-preptroyjthomas/ios-agent-skills | Skill | 2 | 5mo ago | MIT | A | 59 | Claude Code, Codex |