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 Nagarjuna2997/ios-agent-skill --skill ios-buildergit clone --depth 1 https://github.com/Nagarjuna2997/ios-agent-skillWrote 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/nagarjuna2997/ios-agent-skill/ios-builder)<a href="https://agentmods.dev/skills/nagarjuna2997/ios-agent-skill/ios-builder"><img src="https://agentmods.dev/badge/skills/nagarjuna2997/ios-agent-skill/ios-builder/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/nagarjuna2997/ios-agent-skill/ios-builder"><img src="https://agentmods.dev/badge/skills/nagarjuna2997/ios-agent-skill/ios-builder.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 | $0.00053 | $0.00623 |
| Opus 5 | $0.00026 | $0.00311 |
| Sonnet 5 | $0.00011 | $0.00125 |
| Haiku 4.5 | $0.00005 | $0.00062 |
Grade A, and why
ios-builder 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.
What it actually says
Build an Apple App
Turn the user's idea into a working, tested implementation in their available coding environment. Start with the existing project when present; otherwise use a new directory. Make routine design choices and record assumptions. Ask only for missing information that materially blocks the app, such as required service credentials.
- Read
docs/tooling/app-description-workflow.mdand define the user flows, screens, data, and acceptance criteria from the brief. - Read
docs/tooling/offline-source-library.mdand search local source first. With terminal access usenode scripts/query-library.mjs search "feature"; read only needed sections or complete source files. Find frameworks indocs/apple/all-technologies.md. Load only relevant guides. Consultdocs/apple/updates-and-release-notes.mdfor SDK changes and use source dates honestly. - With terminal access, scaffold via
npx -y @nagarjuna2002/[email protected] new AppName --brief "the app idea" --xcodegen. Use a validated Swift identifier for AppName and pass user text as an argument rather than interpolating it into shell syntax. Read the generatedApp/APP_BRIEF.mdand implement it; the scaffolder itself does not generate the finished product from natural language. - Implement features using the existing app architecture. Use
templates/andpatterns/only where appropriate. Add real loading, empty, error and populated states; provide preview data and keep live service dependencies injectable. - Read
docs/design/icon-composer.md. Create and customize separate SVG/PNG foreground layers plus a background decision. Use Icon Composer to annotate and verify the native document when available. Never claim a flattened image or renamed JSON is a native layered icon. - Generate the project with XcodeGen when using that scaffold, build with the actual Xcode SDK, run meaningful tests, then inspect app screens and accessible interactions. Fix failures before reporting completion.
- Report files changed, runnable commands, test/build evidence, and anything needing credentials, hardware or user decisions. Do not publish an app or create paid service resources without the user's authorization.
If the environment lacks filesystem or Xcode access, deliver the concrete plan/source artifacts it can support and explain what must run in a local coding environment. A plugin installation is not evidence that an app has been built. These bundled references are a dated snapshot; consult linked official sources for changing APIs.
For optional local Simulator control and a browser/sidebar preview, read docs/tooling/ios-simulator-mcp.md. Inspect installed device profiles before claiming support for a newly announced phone; current Duo guidance is in docs/platforms/iphone-duo.md. Runtime control requires a local Mac with Xcode.
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 · 21 lines · 53 tokens per session scan A 34c2f7ca5733
ios-builder is a skill published in the GitHub repository Nagarjuna2997/ios-agent-skill (33 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 623 once invoked, about $0.0003 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 2026-09-11.
Other skills, from other repositories
swift-expert
Expert-level Swift development for iOS, macOS with SwiftUI, Combine, and modern Swift 5.9+. Use when the user mentions iOS, macOS, SwiftUI, Combine, async await, or Apple platforms, or when the task involves Modern Swift Features, Basics and Optionals, Functions and Closures, or Structs and Classes.
ios-expert
Expert in iOS development with SwiftUI, UIKit, Combine, and Apple ecosystem integration. Use when the user mentions mobile, Swift, SwiftUI, UIKit, Apple platforms, or Xcode, or when the task involves iOS App Architecture, SwiftUI Fundamentals, UIKit Essentials, or Combine Framework.
swift-architecture-skill
Swift iOS architecture guidance and playbooks for MVVM, MVI, TCA, Clean Architecture, VIPER, MVP, Coordinator, and Reactive patterns. Use when designing, implementing, refactoring, or reviewing the architecture of a SwiftUI or UIKit feature, module, or codebase.
antigravity-root
Enterprise-grade iOS development workflow for TTBaseUIKit-powered apps. Cross-functional product analysis | MVVM-C Architecture | UIKit + SwiftUI | TTViewCodable | TTBaseSUI | xcodebuild CLI Verification | Zero Regression | iOS 14+.
Swift Patterns
Use this skill when working on Swift projects (SwiftPM packages, iOS/macOS apps) and you want consistent patterns for concurrency, structure, and safety.
swift-kmp
KMP bridge standards for iOS. USE FOR: structuring a bridge layer between Kotlin Multiplatform (KMP) and Swift; integrating KMP iOS framework APIs in a Swift app (direct integration or SwiftPM); handling SKIE flows and sealed classes; mapping Kotlin models/errors to Swift domain types; keeping KMP imports confined to…