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 Xopoko/build-swift-apps --skill swiftui-performance-inspectorgit clone --depth 1 https://github.com/Xopoko/build-swift-appsWrote 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/xopoko/build-swift-apps/swiftui-performance-inspector)<a href="https://agentmods.dev/skills/xopoko/build-swift-apps/swiftui-performance-inspector"><img src="https://agentmods.dev/badge/skills/xopoko/build-swift-apps/swiftui-performance-inspector/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/xopoko/build-swift-apps/swiftui-performance-inspector"><img src="https://agentmods.dev/badge/skills/xopoko/build-swift-apps/swiftui-performance-inspector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00040 | $0.00587 |
| Opus 5 | $0.00020 | $0.00293 |
| Sonnet 5 | $0.00008 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
swiftui-performance-inspector 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 10d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SwiftUI Performance Inspector
Diagnose from code first, then request profiling evidence when code review cannot explain the symptom.
Workflow
- Classify the symptom: slow rendering, scrolling jank, high CPU, memory growth, hangs, broad updates, or layout thrash.
- If code is available, review with
references/code-smells.md. - If code is missing, ask for the smallest useful slice: target view, data flow, reproduction steps, device/simulator, build config, and deployment target.
- If runtime evidence is needed, use
references/profiling-intake.mdfor the exact Instruments checklist. - Report likely causes, evidence, fixes, and validation steps using
references/report-template.mdwhen useful.
Code Review Focus
- invalidation storms from broad observation or environment reads
- unstable identity in
List/ForEach - heavy derived work in
bodyor view builders - layout thrash from complex hierarchy,
GeometryReader, or preferences - main-thread image decode/resize or other expensive work
- animation and transition work applied too broadly
Profiling Evidence
Ask for SwiftUI timeline or Time Profiler export/screenshots, device/OS/build configuration, exact profiled interaction, and before/after metrics when comparing changes.
Map evidence to invalidation, identity churn, layout, main-thread work, image cost, animation cost, or hangs. Distinguish trace-backed findings from code-level suspicion and state what evidence would reduce uncertainty.
Fix Defaults
- narrow state scope and observation fan-out
- stabilize list identities
- move heavy work out of
bodyinto model/service precomputation, memoized helpers, background preprocessing, or input-driven derived state - use
@Stateonly for view-owned state, not arbitrary caches - use
equatable()only when equality is cheaper than recomputing and inputs are value-semantic - downsample images before rendering
- reduce layout complexity or add stable sizing where appropriate
Output
Provide a short metrics table when available, top issues ordered by impact, proposed fixes with effort, and verification steps.
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.
- agents/openai.yaml 290 B
- references/code-smells.md 3.7 KB
- references/demystify-swiftui-performance-wwdc23.md 1.8 KB
- references/optimizing-swiftui-performance-instruments.md 1.8 KB
- references/profiling-intake.md 1.9 KB
- references/report-template.md 1.2 KB
- references/understanding-hangs-in-your-app.md 1.2 KB
- references/understanding-improving-swiftui-performance.md 2.2 KB
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.
- 10d ago First seen · 58 lines · 40 tokens per session scan A ad3ca601ee1f
swiftui-performance-inspector is a skill published in the GitHub repository Xopoko/build-swift-apps (45 stars, last pushed 13d ago), licensed MIT. It adds 40 tokens to every session and 587 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 2026-08-30.
Other skills, from other repositories
firebase-crashlytics
Use when implementing crash reporting, capturing fatal/non-fatal errors, recording isolate/async exceptions, customizing reports, or uploading obfuscated symbols.
flutter-errors
Use when hitting layout errors (RenderFlex overflow, unbounded constraints, RenderBox not laid out), scroll errors, or setState-during-build errors.
push-notification-tester
Test VoIP push notifications for Telnyx WebRTC iOS (APNs) and Android (FCM) apps. Use when debugging push notification delivery, validating certificate/credential setup, or testing that a device receives VoIP pushes correctly.
mobile-emulator-start
Boot Android emulator + Metro (Expo / bare RN) in order: inspect IDE terminals, kill stale ports, pick an AVD. Use when "start Metro", "start emulator", "Cannot connect to Expo", or a stuck dev loop. QA on the running emulator → mobile-emulator-test.
apple-cleanup
Exhaustive engineering hardening of an iOS app. Reviews for Swift 6 compliance, crash risks, App Store rejection risks, and tech debt; builds a surgical plan; dispatches parallel subagents to fix all P0-P2 issues; then pushes an alpha to TestFlight. Use for pre-submission cleanup and code hardening, not design polish.
apple-polish
Design and keynote-readiness craftsmanship review of an iOS app. Evaluates through Jony Ive (visual obsession) and Steve Jobs (demo readiness) perspectives, presents prioritized findings, then orchestrates parallel agents to fix selected issues and push a TestFlight build. Use for design polish, not engineering bugs.