Borrowing it
Nothing to install: this file belongs to alessiorubicini/Apple-Foundation-Models-Agent-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.
curl -O https://raw.githubusercontent.com/alessiorubicini/Apple-Foundation-Models-Agent-Skill/main/AGENTS.mdgit clone --depth 1 https://github.com/alessiorubicini/Apple-Foundation-Models-Agent-SkillWrote 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/alessiorubicini/apple-foundation-models-agent-skill/agents-md)<a href="https://agentmods.dev/instructions/alessiorubicini/apple-foundation-models-agent-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/alessiorubicini/apple-foundation-models-agent-skill/agents-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/alessiorubicini/apple-foundation-models-agent-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/alessiorubicini/apple-foundation-models-agent-skill/agents-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 | $0.01263 | $0.01263 |
| Opus 5 | $0.00632 | $0.00632 |
| Sonnet 5 | $0.00253 | $0.00253 |
| Haiku 4.5 | $0.00126 | $0.00126 |
Grade A, and why
Apple-Foundation-Models-Agent-Skill 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 9d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Foundation Models Skill: Agent Author Guide
This document defines the content contract for apple-foundation-models-skill.
Read this before contributing or modifying any reference file.
Purpose
This skill enhances agent reasoning about Apple's FoundationModels framework by providing:
- Accurate API surface — no hallucinated types, methods, or parameters.
- Correctness invariants — rules the agent must enforce in generated code.
- Decision trees — routing logic so the agent selects the right reference file.
- Boundary enforcement — explicit list of what this skill does NOT cover.
How This Skill Enhances Agent Reasoning
When a user asks the agent to write, review, or debug FoundationModels code, the agent:
- Reads
SKILL.mdto load the mental model and active invariants. - Consults
references/_index.mdto identify which reference files apply. - Pulls the relevant reference(s) for the specific API surface involved.
- Applies the correctness invariants before emitting any code.
This layered approach keeps SKILL.md token-efficient (fast to load) while ensuring deep accuracy for complex tasks (reference files loaded on demand).
Content Boundaries
This skill covers
- All public API in the
FoundationModelsframework (iOS 26.0+ stable, iOS 27.0+ beta when explicitly marked) - Public WWDC 2026 beta surfaces: prompt attachments, dynamic profiles, session properties, Private Cloud Compute models, custom language model providers, reasoning/context options, and beta error handling
- Concurrency patterns specific to
LanguageModelSessionandTool - Integration with SwiftUI
@State,@Observable, and.task - Error handling for
LanguageModelSession.GenerationErrorand betaLanguageModelError - Performance patterns unique to on-device LLM inference
This skill does NOT cover
- General Swift Concurrency → use the Swift Concurrency Skill
- General SwiftUI patterns → use the SwiftUI Expert Skill
- CoreML, Create ML, or Vision framework
- Private Cloud Compute service internals, infrastructure, non-public endpoints, or server deployment
- Third-party LLM SDKs (OpenAI, Anthropic, etc.)
- LoRA adapter training (Python toolkit — not the Swift API)
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.
- 9d ago First seen · 124 lines · 1,263 tokens per session scan A 590ae015d183
Apple-Foundation-Models-Agent-Skill AGENTS.md is an instructions file published in the GitHub repository alessiorubicini/Apple-Foundation-Models-Agent-Skill (13 stars, last pushed 2mo ago), licensed MIT. It adds 1,263 tokens to every session, about $0.0063 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.
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.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.