project-structure

A project-organization guide for iOS apps built with SwiftUI, Apple’s framework for creating app interfaces. It explains where source files, tests, notes, AI instructions, and Xcode project files belong.

In plain words
What is it for?
Use it when setting up, reviewing, or maintaining the directory structure of a SwiftUI app and its tests.
Why use it?
It prevents files and project instructions from being scattered or missing from the Xcode project.

Skill for Claude CodeCodex

Part of the meta-loop-ios plugin — 4 skills, 5 commands shipped together

Install

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.

agentmods
npx agentmods add skills/jpavley/meta-loop-ios/project-structure
Any agent
npx skills add jpavley/meta-loop-ios --skill project-structure
Clone the repo
git clone --depth 1 https://github.com/jpavley/meta-loop-ios

Made for: Claude Code, Codex.

Or install meta-loop-ios, the plugin that ships this one along with the rest of its 4 skills, 5 commands.

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,824 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.01824
Opus 5 $0.00009 $0.00912
Sonnet 5 $0.00004 $0.00365
Haiku 4.5 $0.00002 $0.00182

Measured 2d ago against content hash 0b686ff5b8c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-structure 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 2d 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.

skills/project-structure/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Structure

How meta-loop artifacts fit into an iOS/SwiftUI Xcode project. Covers directory layout, who creates each file, and what belongs in the Xcode project navigator.

Directory Layout

MyApp/                              # Git repo root
├── MyApp.xcodeproj                 # Xcode project (you create)
├── MyApp/                          # Swift source (you + AI create)
│   ├── MyAppApp.swift
│   ├── ContentView.swift
│   └── Views/
│       └── FeatureView.swift
├── MyAppTests/                     # Test source (you + AI create)
├── CLAUDE.md                       # AI agent file (ml-setup creates, you maintain)
├── PROJECT-NOTES.md                # Session notes (ml-setup creates, you maintain)
├── PROJECT-TODO.md                 # Task tracking (ml-setup creates, you maintain)
├── README.md                       # Project readme (ml-setup creates, you maintain)
├── .claude/                        # Claude Code config (install.sh creates)
│   ├── commands/                   # Slash commands
│   │   ├── ml-setup.md
│   │   ├── ml-wireframe.md
│   │   ├── ml-spec.md
│   │   ├── ml-impl.md
│   │   └── ml-retain.md
│   ├── skills/                     # Reference docs
│   │   ├── meta-loop-methodology/
│   │   │   ├── SKILL.md
│   │   │   └── meta-loop-diagram.png
│   │   ├── wireframe-design/
│   │   │   └── SKILL.md
│   │   ├── view-specifications/
│   │   │   └── SKILL.md
│   │   └── project-structure/
│   │       └── SKILL.md
│   └── settings.json               # MCP servers, permissions (you create)
├── specs/                          # Specifications (ml-setup creates dir)
│   └── views/                      # View specs
│       └── feature-name/           # One directory per feature
│           ├── *-wireframe.png     # You create (drawing tool, one or more)
│           ├── about-this-view.md  # You create (optional context)
│           ├── spec.md             # ml-spec generates
│           └── notes.md            # ml-spec generates, you + AI update
├── supporting-docs/                # App-level context (ml-setup creates dir)
│   └── about-this-app.md          # You create
└── doc/                            # Retained learnings (ml-retain creates dir)
    ├── SHARED-PATTERNS.md          # ml-retain generates (optional)
    └── DECISIONS.md                # ml-retain generates (optional)

Read the full file on GitHub · 147 lines

Changes

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.

  1. 2d ago First seen · 147 lines · 18 tokens per session scan A 0b686ff5b8c4

Subscribe to this mod's changes

project-structure is a skill published in the GitHub repository jpavley/meta-loop-ios (3 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 1,824 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

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.

efremidze/swift-architecture-skill · 65 tokens

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+.

tqtuan1201/TTBaseUIKit · 57 tokens

ios-app-builder

Implement or finish a production-grade Swift and SwiftUI app from an accepted product specification. Use when creating Xcode targets, models, persistence, navigation, responsive views, imports/exports, StoreKit 2, privacy manifests, accessibility, migrations, error handling, tests, or replacing prototype behavior with…

MartinPuli/createAnApp · 69 tokens

swiftui-compose

Compose Multiplatform ↔ SwiftUI integration patterns. USE FOR: embedding Compose Multiplatform views in a SwiftUI app; embedding SwiftUI/UIKit components inside Compose Multiplatform; sharing state between Compose and SwiftUI; managing the Compose UIViewController lifecycle; bidirectional data flow with the…

sorunokoe/swiftui-compose-skill · 65 tokens

location-maps

涉及地图、定位、CoreLocation、MapKit、CLLocationManager、地理围栏、后台定位、Significant Location Changes、iBeacon 的任务.

wangjianqi/AppStore · 36 tokens

widget-live-activity

涉及 Widget、WidgetKit、Live Activity、ActivityKit、Dynamic Island、灵动岛、桌面小组件、锁屏小组件的开发任务.

wangjianqi/AppStore · 36 tokens