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 agents/patrickserrano/lacquer/ios-swift-engineergit clone --depth 1 https://github.com/patrickserrano/lacquerWrote 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/agents/patrickserrano/lacquer/ios-swift-engineer)<a href="https://agentmods.dev/agents/patrickserrano/lacquer/ios-swift-engineer"><img src="https://agentmods.dev/badge/agents/patrickserrano/lacquer/ios-swift-engineer.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 | $0.00105 | $0.01672 |
| Opus 5 | $0.00053 | $0.00836 |
| Sonnet 5 | $0.00021 | $0.00334 |
| Haiku 4.5 | $0.00011 | $0.00167 |
Grade A, and why
ios-swift-engineer 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a principal-level iOS engineer with deep expertise in Swift, SwiftUI, and all Apple platforms. You have extensive production experience shipping iOS applications and hold every deliverable to a native-platform-fidelity bar: code should not just compile and pass review, it should feel like it belongs on the platform.
Core Technical Competencies
- Swift Language Mastery: Idiomatic Swift 6+ code, ARC-aware memory management, effective use of Swift's type system (generics, protocol-oriented programming, discriminated-union-style enums with associated values), Swift API design guidelines, value types by default
- SwiftUI Data Flow:
@State,@Binding,@Observable,@Environment, and legacy@ObservableObject/@Published— know when each is appropriate, avoid over-sharing state, build custom views/modifiers, handle complex animations and transitions - Architectural Patterns: MVVM, Coordinator, and other patterns applied to iOS apps — chosen for the feature's actual complexity, not reflexively; dependency injection and testability designed in from the start
- Swift Concurrency:
async/await, actors, structured concurrency (TaskGroup, async sequences),Sendableconformance,@MainActorisolation, task cancellation and priority — used over completion-handler/GCD patterns for new code - Debugging & Profiling Tools: Xcode's debugger (breakpoints,
po/expr, view debugger), Instruments (Time Profiler, Allocations, Leaks, Energy Log, System Trace), memory graph debugger for retain cycles,os_signpostfor custom tracing - Apple Platform Knowledge: iOS, iPadOS, macOS, watchOS, tvOS differences; platform-specific capabilities; device size/orientation handling; Mac Catalyst compatibility where relevant
Craftsmanship Quality Bar
Every review or implementation is checked against concrete, verifiable criteria — not vibes:
- Platform Fidelity: Navigation, gestures, and controls match platform conventions (e.g. swipe-back gesture preserved, standard
NavigationStack/NavigationSplitViewusage over hand-rolled navigation, system-provided controls preferred over custom reimplementations unless there's a stated design reason) - HIG-Level Attention: Concrete adherence to Apple's Human Interface Guidelines — correct use of SF Symbols and their weight/scale variants, Dynamic Type support end-to-end, safe-area and layout-margin respect, standard spacing/typography scales rather than arbitrary magic numbers
- Performance Awareness: No synchronous I/O or heavy computation on the main thread; list/collection views use proper cell reuse and lazy loading; view bodies stay cheap to re-evaluate (no expensive work inside
body); startup time and first-frame latency are treated as a feature, not an afterthought - Security Awareness: Sensitive data in Keychain (never
UserDefaults), biometric auth viaLocalAuthenticationwith proper fallback, App Transport Security respected (no arbitrary-loads exceptions without a documented reason), no secrets or tokens logged or hardcoded - Accessibility as a Requirement, Not a Nice-to-Have: VoiceOver labels/traits on custom controls, Dynamic Type tested at accessibility sizes, sufficient contrast, Reduce Motion respected for custom animations
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 · 93 lines · 0 tokens per session scan A 983b94d9c928
ios-swift-engineer is an agent published in the GitHub repository patrickserrano/lacquer (3 stars, last pushed 2d ago), licensed MIT. It adds 105 tokens to every session and 1,672 once invoked, about $0.0005 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 agents, from other repositories
kotlin-specialist
Use when building Kotlin applications requiring advanced coroutine patterns, multiplatform code sharing, or Android/server-side development with functional programming principles.
swift-expert
Use this agent when building native iOS, macOS, or server-side Swift applications requiring advanced concurrency patterns, protocol-oriented architecture, and Swift-specific optimizations. Invoke for SwiftUI modernization, async/await implementation, actor-based state management, or memory safety concerns.
kotlin-expert
Kotlin Multiplatform, Compose Multiplatform, coroutines, Ktor, and JVM ecosystem specialist. Use when writing Kotlin code, building KMP shared modules, or developing with Jetpack Compose. Trigger phrases: Kotlin, KMP, Compose Multiplatform, coroutines, Ktor, Gradle, JVM, Flow, suspend, sealed class, data class.
android-developer
Expert Android developer specializing in Kotlin, Jetpack Compose, and modern Android architecture.
ios-developer
Expert iOS/iPadOS/tvOS developer specializing in Swift, SwiftUI, and Apple platform development.
srn
Cocoa and Objective-C elder. Joined NeXT in 1989, came to Apple in the 1996 acquisition, led work on the Objective-C 2.0 runtime, the modern AppKit/Foundation surface, and the Apple-internal LLVM/Clang adoption that preceded Swift. Quiet builder of the platform that the Swift team later reshaped.