FoundationChat CLAUDE.md

Repository instructions for FoundationChat, a SwiftUI iOS example app that uses Apple’s on-device AI framework for chat features.

In plain words
What is it for?
Use it when adding or changing chat behavior, model sessions, availability checks, error handling, safety code, or performance-related code.
Why use it?
They explain the project structure, supported Apple platforms, required framework rules, and common implementation patterns.

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/dimillian/foundationchat/claude-md
Clone the repo
git clone --depth 1 https://github.com/Dimillian/FoundationChat
Per session 1,511 This file is loaded in full into every session.
When invoked 1,511 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 $0.01511 $0.01511
Opus 5 $0.00756 $0.00756
Sonnet 5 $0.00302 $0.00302
Haiku 4.5 $0.00151 $0.00151

Measured 2d ago against content hash 2abb87a546bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

FoundationChat 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 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.

CLAUDE.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

FoundationChat is a SwiftUI application demonstrating Apple's Foundation Models framework for on-device AI. The project targets iOS 26.0+ and showcases chat functionality using Apple Intelligence.

Framework Overview

Apple's Foundation Models framework provides on-device large language models that power Apple Intelligence. It's available on iOS 26.0+, iPadOS 26.0+, macOS 26.0+, and visionOS 26.0+.

Key Documentation Files

1. EXAMPLES/FOUNDATION_MODELS_RULES.md

When to use: Start here for understanding core framework principles

  • Availability checking patterns
  • Session management rules
  • Performance optimization guidelines
  • Safety implementation requirements
  • Platform requirements and limitations

2. EXAMPLES/QUICK_REFERENCE.md

When to use: For quick code snippets and common patterns

  • Import statements
  • Basic usage patterns
  • Error handling snippets
  • Common configurations

3. EXAMPLES/01_Basic_Usage.md

When to use: For simple text generation tasks

  • Creating sessions
  • Basic prompting
  • Handling availability states
  • Error handling basics
  • Multi-turn conversations

4. EXAMPLES/02_Structured_Output.md

When to use: When you need structured data from the model

  • @Generable macro usage
  • @Guide annotations
  • Complex nested structures
  • Optional properties
  • Performance considerations

5. EXAMPLES/03_Streaming_Responses.md

When to use: For real-time UI updates during generation

  • Basic streaming implementation
  • Streaming with structured output
  • Progress tracking
  • Error handling in streams
  • SwiftUI integration

6. EXAMPLES/04_Tool_Calling.md

When to use: When the model needs external data/actions

  • Tool protocol implementation
  • Integration with system frameworks (Contacts, Calendar, etc.)
  • Stateful tools
  • Multiple tool usage

7. EXAMPLES/05_Performance_and_Safety.md

When to use: For optimization and safety implementation

  • Prewarming strategies
  • Schema optimization
  • Safety boundaries
  • Context management
  • Performance monitoring

Read the full file on GitHub · 209 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 · 209 lines · 1,511 tokens per session scan A 2abb87a546bc

Subscribe to this mod's changes

FoundationChat CLAUDE.md is an instructions file published in the GitHub repository Dimillian/FoundationChat (347 stars, last pushed 1y ago), licensed MIT. It adds 1,511 tokens to every session, about $0.0076 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.

Related

Other instructions, from other repositories