AppBootstrapAI: Instructions file for Claude Code

CLAUDE.md

AppBootstrapAI CLAUDE.md is an instructions file for Claude Code from kelvinkosbab/AppBootstrapAI. It costs 11,402 tokens per session, scanned A, original, MIT.

A bundle of Claude Code rules and skills for starting and maintaining Apple and Android app projects. It is copied into an app repository so Claude Code can use its guidance.

In plain words
What is it for?
Use it when bootstrapping or updating iOS, macOS, tvOS, watchOS, visionOS, or Android apps with Swift, SwiftUI, Kotlin, or Jetpack Compose.
Why use it?
It gives projects shared instructions for architecture, coding style, testing, accessibility, and platform-specific work instead of rebuilding those rules each time.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is kelvinkosbab/AppBootstrapAI's own configuration. It tells Claude Code how to work on AppBootstrapAI itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AppBootstrapAI configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kelvinkosbab/AppBootstrapAI. 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/kelvinkosbab/AppBootstrapAI/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/kelvinkosbab/AppBootstrapAI

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.

agentmods badge for AppBootstrapAI CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kelvinkosbab/appbootstrapai/claude-md.svg)](https://agentmods.dev/instructions/kelvinkosbab/appbootstrapai/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kelvinkosbab/appbootstrapai/claude-md"><img src="https://agentmods.dev/badge/instructions/kelvinkosbab/appbootstrapai/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 11,402 This file is loaded in full into every session.
When invoked 11,402 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 5.1 $0.11402 $0.11402
Opus 5 $0.05701 $0.05701
Sonnet 5 $0.02280 $0.02280
Haiku 4.5 $0.01140 $0.01140

Measured 6d ago against content hash ab94430aad50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

AppBootstrapAI 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 6d 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 · 516 lines

How it starts

The opening of the file, as written. The whole thing — 516 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project Overview

AppBootstrapAI is a drop-in bundle of Claude Code skills and AI steering rules for bootstrapping new app projects. Covers Apple platforms (iOS, macOS, tvOS, watchOS, visionOS — Swift 6.4 concurrency, SwiftUI, Swift Testing, Foundation Models, Objective-C) and Android (Kotlin, Jetpack Compose, MVVM, Hilt, coroutines) in one bundle. Skills (deep-dive review agents) ship for both sides — 10 Apple, 7 Android — alongside the always-loaded steering rules.

This repo is not a Swift package. It is a collection of .claude/ assets intended to be copied (or referenced) into a target app repository so that Claude Code picks up consistent review, testing, and style guidance across projects.

What's in the box

.claude/
├── rules/                         # Always-loaded AI steering (Cursor-style rule files)
│   ├── android-accessibility-best-practices.md    # Android: TalkBack / Compose semantics
│   ├── android-ai-best-practices.md               # Android: Gemini Nano / ML Kit GenAI / Firebase AI Logic
│   ├── android-compose-best-practices.md          # Android: Jetpack Compose patterns
│   ├── android-coroutines-best-practices.md       # Android: Kotlin coroutines / structured concurrency
│   ├── android-documentation-strategy.md          # Android: KDoc strategy + Dokka
│   ├── android-gradle-conventions.md              # Android: Gradle DSL / version catalogs / modules
│   ├── android-large-screen-best-practices.md     # Android: tablets / foldables (tablet-gated)
│   ├── android-linting-strategy.md                # Android: ktlint + detekt + Android Lint
│   ├── android-localization-best-practices.md     # Android: strings.xml / plurals / RTL
│   ├── android-logging-strategy.md                # Android: Timber, levels, release-stripping
│   ├── android-play-beta-deployment.md            # Android: Play beta tracks, signing, CI
│   ├── android-project-rules.md                   # Android: Kotlin/Compose/MVVM/Hilt
│   ├── android-testing-strategy.md                # Android: test strategy + JaCoCo
│   ├── apple-accessibility-best-practices.md      # Apple: SwiftUI a11y
│   ├── apple-documentation-strategy.md            # Apple: DocC strategy + deprecation
│   ├── apple-foundation-models.md                 # Apple: On-device LLM (FoundationModels)
│   ├── apple-linting-strategy.md                  # Apple: SwiftLint + formatter discipline
│   ├── apple-localization-best-practices.md       # Apple: String Catalogs / plurals / RTL
│   ├── apple-logging-strategy.md                  # Apple: os.Logger, privacy markers, levels
│   ├── apple-modular-architecture.md              # Apple: thin app shell + fat local SPM package
│   ├── apple-objc-accessibility-best-practices.md # Apple: UIKit a11y in Objective-C
│   ├── apple-objc-best-practices.md               # Apple: Modern Objective-C
│   ├── apple-spm-package-conventions.md           # Apple: Package.swift authoring
│   ├── apple-swift6-strict-concurrency.md         # Apple: Swift 6.4 strict concurrency
│   ├── apple-swiftui-mvvm.md                      # Apple: SwiftUI MVVM conventions
│   ├── apple-testflight-deployment.md             # Apple: TestFlight, ASC API, signing, CI
│   ├── apple-testing-strategy.md                  # Apple: test strategy + coverage
│   ├── apple-visionos-best-practices.md           # Apple: visionOS / RealityKit / spatial UX
│   ├── concise-comments-and-commits.md            # Cross-platform: terse comments + commits
│   └── project-documentation.md                   # Cross-platform: README/CHANGELOG/ADR
├── skills/                        # On-demand Claude Code skills
│   ├── android-accessibility-pro/          # Android: TalkBack / keyboard / contrast audit
│   ├── android-adaptive-layout-pro/        # Android: large-screen / foldable audit (tablet-gated)
│   ├── android-compose-pro/                # Android: Compose deep review
│   ├── android-coroutines-pro/             # Android: coroutines/Flow deep review
│   ├── android-gradle-architecture-pro/    # Android: NiA-style convention plugins
│   ├── coredata-swift6-pro/                # Apple: Core Data under Swift 6
│   ├── r8-shrink-pro/                      # Android: ProGuard/R8 rules
│   ├── swift-accessibility-pro/            # Apple: VoiceOver / keyboard / contrast audit
│   ├── swift-concurrency-pro/              # Apple: Swift concurrency review
│   ├── swift-docc-pro/                     # Apple: DocC documentation
│   ├── swift-error-handling-pro/           # Apple: typed throws, Result
│   ├── swift-logging-pro/                  # Apple: os.Logger review
│   ├── swift-package-pro/                  # Apple: SPM library design
│   ├── swift-testing-pro/                  # Apple: Swift Testing code
│   ├── swiftdata-pro/                      # Apple: SwiftData review
│   ├── swiftui-pro/                        # Apple: SwiftUI review
│   └── xml-to-compose-migration-pro/       # Android: XML/Fragment → Compose
└── settings.json                  # Baseline Claude Code permissions (git, xcodebuild, gradlew, etc.)

Read the full file on GitHub · 516 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. 6d ago First seen · 516 lines · 11,402 tokens per session scan A ab94430aad50

Subscribe to this mod's changes

AppBootstrapAI CLAUDE.md is an instructions file published in the GitHub repository kelvinkosbab/AppBootstrapAI (5 stars, last pushed 15d ago), licensed MIT. It adds 11,402 tokens to every session, about $0.0570 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens