Swift-Foundation-Models-Skills AGENTS.md

Swift-Foundation-Models-Skills AGENTS.md is an instructions file for Codex, OpenCode from sambitcreate/Swift-Foundation-Models-Skills. It costs 1,534 tokens per session, scanned A, original, MIT.

A set of instructions for building Apple-platform apps with Apple's Foundation Models framework, which provides on-device AI features for iOS and macOS. It covers conversations, structured output, token limits, and model-connected tools.

In plain words
What is it for?
It helps set up and check Foundation Models, manage single- and multi-turn sessions, stream responses, control context budgets, generate typed Swift data, create dynamic schemas, and build custom tools.
Why use it?
The framework has separate concerns for model availability, sessions, streaming, data formats, and system integration. These instructions collect the relevant implementation patterns in one place.

Instructions file for CodexOpenCode

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/sambitcreate/swift-foundation-models-skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/sambitcreate/Swift-Foundation-Models-Skills

Made for: Codex, OpenCode.

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 Swift-Foundation-Models-Skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sambitcreate/swift-foundation-models-skills/agents-md.svg)](https://agentmods.dev/instructions/sambitcreate/swift-foundation-models-skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/sambitcreate/swift-foundation-models-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/sambitcreate/swift-foundation-models-skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,534 This file is loaded in full into every session.
When invoked 1,534 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 $0.01534 $0.01534
Opus 5 $0.00767 $0.00767
Sonnet 5 $0.00307 $0.00307
Haiku 4.5 $0.00153 $0.00153

Measured 5d ago against content hash 8df575d64184, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Swift-Foundation-Models-Skills AGENTS.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 5d 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.

AGENTS.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apple Foundation Models Skills Repository

This repository contains a collection of skills for building iOS/macOS applications with Apple's Foundation Models framework (Apple Intelligence). Each skill focuses on a specific use case or pattern for working with on-device AI.

Skills Overview

Core Session Management

Skill Description
apple-foundation-models-setup-availability Check model availability and set up Foundation Models
apple-foundation-models-session-patterns Create sessions for single-turn and multi-turn conversations
apple-foundation-models-streaming-chat-context Stream responses and manage context window
apple-foundation-models-token-budget-management Count tokens and manage context budgets

Structured Generation

Skill Description
apple-foundation-models-structured-generation Generate type-safe Swift structs with @Generable
apple-foundation-models-dynamic-schemas Build schemas dynamically at runtime

Tools & System Integration

Skill Description
apple-foundation-models-custom-tools Build custom tools the model can call
apple-foundation-models-system-tools Use built-in system tools (weather, contacts, calendar)
apple-foundation-models-health-assistant HealthKit integration with custom tools

Context & Conversation

Skill Description
apple-foundation-models-conversation-context-builder Extract context and build continuation prompts
apple-foundation-models-swiftdata-persistence Persist conversations with SwiftData

Read the full file on GitHub · 176 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. 5d ago First seen · 176 lines · 1,534 tokens per session scan A 8df575d64184

Subscribe to this mod's changes

Swift-Foundation-Models-Skills AGENTS.md is an instructions file published in the GitHub repository sambitcreate/Swift-Foundation-Models-Skills (21 stars, last pushed 6mo ago), licensed MIT. It adds 1,534 tokens to every session, about $0.0077 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

claude-code-apple-skills CLAUDE.md

Claude Code instructions for rshankras/claude-code-apple-skills, covering claude.md, repository purpose, architecture, skill structure and yaml frontmatter (required).

rshankras/claude-code-apple-skills · 859 tokens

maclocal-api AGENTS.md

AGENTS.md instructions for scouzi1966/maclocal-api, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.

scouzi1966/maclocal-api · 1,269 tokens

app-store-connect-mcp AGENTS.md

AGENTS.md instructions for erayendes/app-store-connect-mcp, covering agents.md, what this is, if a user asks you to install it, 1. agree on the profiles, then register them and 2. send the user to setup for the credentials.

erayendes/app-store-connect-mcp · 1,396 tokens

openclip AGENTS.md

Instructions for ganeshmshetty/openclip, covering agents.md, build & test, architecture hard rules, logging and extensions.

ganeshmshetty/openclip · 1,350 tokens

Apple-Foundation-Models-Agent-Skill AGENTS.md

Instructions for alessiorubicini/Apple-Foundation-Models-Agent-Skill, covering agents.md — foundation models skill: agent author guide, purpose, how this skill enhances agent reasoning, content boundaries and this skill covers.

alessiorubicini/Apple-Foundation-Models-Agent-Skill · 1,263 tokens

ios-agent-skills CLAUDE.md

Instructions for troyjthomas/ios-agent-skills, covering ios agent skills v2 - repository configuration, what this is, structure and conventions.

troyjthomas/ios-agent-skills · 229 tokens