SwiftUIAgentToolkit CLAUDE.md

SwiftUIAgentToolkit CLAUDE.md is an instructions file for coding agents from vivqu/SwiftUIAgentToolkit. It costs 681 tokens per session, scanned A, original, MIT.

A project instruction file for building iOS apps with SwiftUI, Apple's framework for app interfaces. It defines the project's architecture, coding rules, naming, and testing practices.

In plain words
What is it for?
Starting SwiftUI projects and guiding work on views, view models, models, asynchronous code, previews, builds, and tests.
Why use it?
It gives coding agents consistent rules to follow when changing the app.

Instructions file

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 instructions/vivqu/swiftuiagenttoolkit/claude-md
Clone the repo
git clone --depth 1 https://github.com/vivqu/SwiftUIAgentToolkit

Wrote 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.

agentmods badge for SwiftUIAgentToolkit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vivqu/swiftuiagenttoolkit/claude-md.svg)](https://agentmods.dev/instructions/vivqu/swiftuiagenttoolkit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/vivqu/swiftuiagenttoolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/vivqu/swiftuiagenttoolkit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 681 This file is loaded in full into every session.
When invoked 681 The same file — it is already loaded in full.
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 $0.00681 $0.00681
Opus 5 $0.00341 $0.00341
Sonnet 5 $0.00136 $0.00136
Haiku 4.5 $0.00068 $0.00068

Measured 3d ago against content hash e064069dbaec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

SwiftUIAgentToolkit CLAUDE.md 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 3d 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.

CLAUDE.md · 58 lines

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.

SwiftUIAgentToolkit

A toolkit for bootstrapping SwiftUI mobile apps — designed for rapid, vibe-coded development.

Project Purpose

A cloneable template for quickly starting new iOS apps with SwiftUI. See docs/SETUP.md for how to create an Xcode project inside this template.

Architecture

  • Swift 5.9+ / SwiftUI — No UIKit unless absolutely necessary
  • Minimum deployment target: iOS 18+
  • Architecture pattern: MVVM with @Observable macro (not ObservableObject)

Coding Standards

  • Use @Observable instead of ObservableObject / @StateObject
  • Prefer @State for local view state, @Environment for dependency injection
  • Extract reusable views into their own files — one view per file
  • Use #Preview macro for previews, not PreviewProvider
  • No force unwraps (!) — use guard let, if let, or provide defaults
  • Async/await for all async work; no callbacks or Combine unless integrating external APIs

Naming Conventions

  • Views: FooView.swift (e.g., HomeView, ProfileView)
  • ViewModels: FooViewModel.swift
  • Models: Foo.swift (plain struct/class names)
  • Extensions: Foo+Bar.swift (e.g., Color+Brand.swift)

Build & Test

Three commands are available for verifying app correctness after code changes. They are provided by the ios-verify-ui plugin — install it with:

claude plugin add https://github.com/vivqu/claude-swift-verify-ui-plugin
  • /ios-verify-ui:verify-ui — Build and run the app on a simulator, take a screenshot, and confirm UI changes look correct. Use after any visual change.
  • /ios-verify-ui:verify-test — Run the unit and UI test suite and report pass/fail results. Use after adding or changing logic with tests.
  • /ios-verify-ui:verify — Full verification: runs both UI and test checks in sequence and reports a combined summary. Use when you want to confirm everything is working end to end.

Prototyping

When building prototype screens that need images, use the /placeholder-ui skill. It provides:

Read the full file on GitHub · 58 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. 3d ago First seen · 58 lines · 681 tokens per session scan A e064069dbaec

Subscribe to this mod's changes

SwiftUIAgentToolkit CLAUDE.md is an instructions file published in the GitHub repository vivqu/SwiftUIAgentToolkit (11 stars, last pushed 5mo ago), licensed MIT. It adds 681 tokens to every session, about $0.0034 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.