What is swift-architecture-skill CLAUDE.md?

A set of instructions for designing and building Swift apps using common architecture patterns such as MVVM, MVI, and Clean Architecture. It covers both SwiftUI and UIKit projects.

Use it to design, implement, refactor, or review iOS screens and modules. It provides guidance for selecting and applying different Swift architecture patterns.

It helps developers choose a suitable way to organise app code and follow consistent project conventions. This reduces guesswork when adding features or restructuring an iOS codebase.

How efremidze/swift-architecture-skill configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to efremidze/swift-architecture-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/efremidze/swift-architecture-skill/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/efremidze/swift-architecture-skill

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/efremidze/swift-architecture-skill/claude-md/github.svg)](https://agentmods.dev/instructions/efremidze/swift-architecture-skill/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/efremidze/swift-architecture-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/efremidze/swift-architecture-skill/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/efremidze/swift-architecture-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/efremidze/swift-architecture-skill/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 439 This file is loaded in full into every session.

When invoked 439 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00439	$0.00439
Opus 5.5	$0.00176	$0.00176
Sonnet 5.5	$0.00088	$0.00088
Haiku 4.5	$0.00044	$0.00044

Measured 1mo ago against content hash 72e0bd857cfd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

swift-architecture-skill 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 1mo 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 · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Swift Architecture Skill

This repository contains an Agent Skill that provides Swift architecture design and implementation patterns for iOS codebases.

Project Structure

.claude-plugin/
  plugin.json                 # Claude Code plugin manifest
  marketplace.json            # Marketplace listing manifest
swift-architecture-skill/     # The Agent Skill itself
  SKILL.md                    # Skill definition and workflow
  references/
    selection-guide.md        # Architecture decision framework
    concurrency.md            # Shared async, cancellation, and error-mapping rules
    observation.md            # Shared @Observable vs ObservableObject guidance
    mvp.md                    # MVP pattern playbook
    mvvm.md                   # MVVM pattern playbook
    mvi.md                    # MVI pattern playbook
    tca.md                    # TCA (Composable Architecture) playbook
    clean-architecture.md     # Clean Architecture playbook
    viper.md                  # VIPER pattern playbook
    coordinator.md            # Coordinator pattern playbook
    reactive.md               # Reactive (Combine/RxSwift) playbook
tooling/                      # Validation scripts, evals, and benchmarks
README.md                     # Installation and usage docs

How the Skill Works

User requests architecture guidance for a Swift feature or module
The skill routes to the appropriate architecture playbook based on explicit request or inferred constraints
The playbook provides concrete patterns, code examples, anti-patterns, testing strategies, and PR review checklists
Output is tailored to the user's specific feature context

Key Conventions

All architecture references are standalone markdown playbooks in references/
Each playbook follows a consistent structure: core concepts, code patterns, anti-patterns with fixes, testing strategy, and PR review checklist
The skill supports MVP, MVVM, MVI, TCA, Clean Architecture, VIPER, Coordinator, and Reactive patterns
When no architecture is specified, use references/selection-guide.md to infer the best fit
Code examples use modern Swift concurrency (async/await, actors) and cover both SwiftUI and UIKit patterns

Read the full file on GitHub · 43 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.

1mo ago Changed · +1 lines · +17 tokens per session 72e0bd857cfd
2mo ago First seen · 42 lines · 422 tokens per session scan A 45c0ac864e42

Subscribe to this mod's changes

swift-architecture-skill CLAUDE.md is an instructions file published in the GitHub repository efremidze/swift-architecture-skill (81 stars, last pushed 1mo ago), licensed MIT. It adds 439 tokens to every session, about $0.0018 per session on Opus 5.5. 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.

Kotlin and Swift Languages Mobile agent agent-skills ios swift swiftui

swift-architecture-skill CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
swift-architecture-skill CLAUDE.mdefremidze/swift-architecture-skill	Instructions file	81	1mo ago	MIT	A	439	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

swift-architecture-skill: Instructions file for Claude Code