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.
curl -O https://raw.githubusercontent.com/kelvinkosbab/AppBootstrapAI/main/CLAUDE.mdgit clone --depth 1 https://github.com/kelvinkosbab/AppBootstrapAIWrote 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/instructions/kelvinkosbab/appbootstrapai/claude-md)<a href="https://agentmods.dev/instructions/kelvinkosbab/appbootstrapai/claude-md"><img src="https://agentmods.dev/badge/instructions/kelvinkosbab/appbootstrapai/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.
<a href="https://agentmods.dev/instructions/kelvinkosbab/appbootstrapai/claude-md"><img src="https://agentmods.dev/badge/instructions/kelvinkosbab/appbootstrapai/claude-md.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 | $0.15395 | $0.15395 |
| Opus 5.5 | $0.06158 | $0.06158 |
| Sonnet 5.5 | $0.03079 | $0.03079 |
| Haiku 4.5 | $0.01540 | $0.01540 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 653 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 — 13 Apple, 9 Android, 2 cross-platform — 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-design-system.md # Android: M3 AppTheme, tokens, core components
│ ├── android-documentation-strategy.md # Android: KDoc strategy + Dokka
│ ├── android-gradle-conventions.md # Android: Gradle DSL / version catalogs / modules
│ ├── android-iconography.md # Android: Material Symbols, adaptive/themed launcher icons
│ ├── 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-modular-architecture.md # Android: thin :app over feature/core modules (NiA)
│ ├── android-mvvm-architecture.md # Android: MVVM / UDF, UiState, Route vs Screen (opt-in)
│ ├── android-play-beta-deployment.md # Android: Play beta tracks, signing, CI
│ ├── android-project-rules.md # Android: Kotlin/Compose/MVVM/Hilt
│ ├── android-regional-compliance.md # Android: per-country Play / China store rules
│ ├── android-repository-pattern.md # Android: data layer / repositories (opt-in)
│ ├── android-testing-strategy.md # Android: test strategy + JaCoCo
│ ├── apple-accessibility-best-practices.md # Apple: SwiftUI a11y
│ ├── apple-adaptive-layout.md # Apple: resizable apps / iPhone Duo
│ ├── apple-design-system.md # Apple: tokens, component styles, Liquid Glass
│ ├── apple-documentation-strategy.md # Apple: DocC strategy + deprecation
│ ├── apple-foundation-models.md # Apple: On-device LLM (FoundationModels)
│ ├── apple-iconography.md # Apple: SF Symbols facade, Icon Composer app icons
│ ├── apple-infoplist-localization.md # Apple: Info.plist / usage-description strings
│ ├── 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-regional-compliance.md # Apple: per-storefront App Store rules
│ ├── apple-repository-pattern.md # Apple: data layer / repositories (opt-in)
│ ├── 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
│ ├── ai-steering-files.md # Cross-platform: CLAUDE.md / AGENTS.md / agent rules
│ ├── concise-comments-and-commits.md # Cross-platform: terse comments + commits
│ ├── cross-platform-development.md # Cross-platform: Apple + Android together with AI (--platform both)
│ └── 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-design-system-pro/ # Android: icons + theme + components bootstrap/audit
│ ├── android-gradle-architecture-pro/ # Android: NiA-style convention plugins
│ ├── android-modularization-pro/ # Android: plan/migrate/audit a multi-module app
│ ├── coredata-swift6-pro/ # Apple: Core Data under Swift 6
│ ├── cross-platform-parity-pro/ # Both: port features, audit drift, set up a two-platform repo
│ ├── r8-shrink-pro/ # Android: ProGuard/R8 rules
│ ├── store-compliance-pro/ # Both: regional store-rejection audit + response
│ ├── swift-accessibility-pro/ # Apple: VoiceOver / keyboard / contrast audit
│ ├── swift-adaptive-layout-pro/ # Apple: resizable / iPhone Duo audit
│ ├── swift-concurrency-pro/ # Apple: Swift concurrency review
│ ├── swift-design-system-pro/ # Apple: icons + tokens + components bootstrap/audit
│ ├── swift-docc-pro/ # Apple: DocC documentation
│ ├── swift-error-handling-pro/ # Apple: typed throws, Result
│ ├── swift-logging-pro/ # Apple: os.Logger review
│ ├── swift-modularization-pro/ # Apple: plan/migrate/audit a local SPM package
│ ├── 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.)
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.
- 3d ago Changed · +13 lines · +394 tokens per session 971c276d26b4
- 4d ago Changed · +1 lines · +104 tokens per session c533de3a1cc1
- 6d ago Changed · +19 lines · +582 tokens per session 3e16071864ae
- 11d ago Changed · +100 lines · +2,824 tokens per session c94235ec0233
- 25d ago Changed · +1 lines · +24 tokens per session df079bc7eae1
- 1mo ago Changed · +3 lines · +65 tokens per session e00652d58133
- 1mo ago First seen · 516 lines · 11,402 tokens per session scan A ab94430aad50
AppBootstrapAI CLAUDE.md is an instructions file published in the GitHub repository kelvinkosbab/AppBootstrapAI (8 stars, last pushed 4d ago), licensed MIT. It adds 15,395 tokens to every session, about $0.0616 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 2026-08-31.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.