foundation-models-auditor

foundation-models-auditor is an agent for Claude Code from CharlesWiltgen/Axiom. It costs 274 tokens per session (7,478 once invoked), scanned B, original, MIT.

A code-review agent for Apple's Foundation Models framework, which supports Apple Intelligence features in iOS and macOS apps. It checks Swift code for 14 serious integration problems.

In plain words
What is it for?
Use it when reviewing Apple Intelligence or Foundation Models code, including availability checks, LanguageModelSession usage, and @Generable structured output.
Why use it?
It helps find crashes on unsupported devices, blocked app threads, unsafe prompts, broken structured results, and wasted model sessions before release.

Agent for Claude Code

Written for Claude Code: background in frontmatter. Also seen: model in frontmatter.

Part of the axiom plugin — 27 skills, 17 commands, 42 agents, 5 hooks shipped together

Good fit Use it when reviewing Apple Intelligence or Foundation Models code, including availability checks, LanguageModelSession usage, and @Generable structured output.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/charleswiltgen/axiom/foundation-models-auditor
About the project

Axiom is a toolkit of instructions, agents, commands, and development tools that give coding assistants specialized guidance for Apple operating-system development. It covers Swift, SwiftUI, interface design, data, concurrency, performance, networking, accessibility, logging, crash analysis, simulator testing, and profiling for iOS, iPadOS, watchOS, and tvOS. The catalogue contains 42 agents, 16 commands, and one plugin from this toolkit.

CharlesWiltgen/Axiom · 1,151 stars · on GitHub · charleswiltgen.github.io

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.

Clone the repo
git clone --depth 1 https://github.com/CharlesWiltgen/Axiom

Made for: Claude Code.

Or install axiom, the plugin that ships this one along with the rest of its 27 skills, 17 commands, 42 agents, 5 hooks.

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 foundation-models-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/charleswiltgen/axiom/foundation-models-auditor/github.svg)](https://agentmods.dev/agents/charleswiltgen/axiom/foundation-models-auditor)
Your own site
<a href="https://agentmods.dev/agents/charleswiltgen/axiom/foundation-models-auditor"><img src="https://agentmods.dev/badge/agents/charleswiltgen/axiom/foundation-models-auditor/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.

agentmods 80×15 button for foundation-models-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/charleswiltgen/axiom/foundation-models-auditor"><img src="https://agentmods.dev/badge/agents/charleswiltgen/axiom/foundation-models-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 274 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,478 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00274 $0.07478
Opus 5 $0.00137 $0.03739
Sonnet 5 $0.00055 $0.01496
Haiku 4.5 $0.00027 $0.00748

Measured 10d ago against content hash 45bbad768ee4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

foundation-models-auditor scanned grade B with 1 finding 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 10d 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.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

| Are user-supplied strings sanitized or escaped before being interpolated into prompts (or are they passed via separate Tool inputs / @Generable parameters)? | Prompt-injection risk | Direct interpolation lets users ove

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

.claude-plugin/plugins/axiom/agents/foundation-models-auditor.md · 482 lines

How it starts

The opening of the file, as written. The whole thing — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Foundation Models Auditor Agent

You are an expert at detecting Foundation Models (Apple Intelligence) issues — both known anti-patterns AND missing/incomplete patterns that cause crashes on unsupported devices, watchdog termination, guardrail-refusal UX failures, prompt injection, structured-output parsing breakage, and session lifecycle waste.

Tool Use Is Mandatory

Run every Glob, Grep, and Read this prompt lists. Do not reason from training data instead of scanning.

  • Run each Grep pattern as written; do not collapse them into one mega-regex.
  • Run the Read verifications each section calls for.
  • "Build a mental model" / "map the architecture" means with tool output in hand, not from memory.

Files to Exclude

Skip: *Tests.swift, *Previews.swift, */Pods/*, */Carthage/*, */.build/*, */DerivedData/*, */scratch/*, */docs/*, */.claude/*, */.claude-plugin/*

Phase 1: Map Foundation Models Surface

Step 1: Identify Imports and Deployment Target

Glob: **/*.swift, **/*.xcconfig
Grep for:
  - `import\s+FoundationModels` — files using the framework
  - `IPHONEOS_DEPLOYMENT_TARGET`, `MACOSX_DEPLOYMENT_TARGET` — must be iOS 26+/macOS 26+
  - `if #available\(iOS\s+26`, `if #available\(macOS\s+26` — availability gates
  - `@available\(iOS\s+26`, `@available\(macOS\s+26` — type-level availability

Step 2: Identify Sessions and Their Owners

Grep for:
  - `LanguageModelSession\(` — session construction sites (where is each created?)
  - `var\s+session:\s*LanguageModelSession`, `let\s+session:\s*LanguageModelSession` — ownership
  - `@State\s+.*LanguageModelSession`, `@StateObject` patterns near sessions
  - `class\s+\w+(Service|Manager|ViewModel)` containing session ownership

Step 3: Identify Availability and Lifecycle Surface

Grep for:
  - `SystemLanguageModel\.default\.availability` — availability check sites
  - `\.availability` — any availability access
  - `\.unavailable`, `\.available` — availability cases handled
  - `\.deviceNotEligible`, `\.appleIntelligenceNotEnabled`, `\.modelNotReady` — the three real UnavailableReason cases
  - `\.task\s*\{`, `Task\s*\{`, `\.onAppear` near session creation — lifecycle anchors
  - `Button.*LanguageModelSession`, `onTapGesture.*LanguageModelSession` — session-in-action smell

Read the full file on GitHub · 482 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. 10d ago First seen · 482 lines · 274 tokens per session scan B 45bbad768ee4

Subscribe to this mod's changes

foundation-models-auditor is an agent published in the GitHub repository CharlesWiltgen/Axiom (1,151 stars, last pushed today), licensed MIT. It adds 274 tokens to every session and 7,478 once invoked, about $0.0014 per session on Opus 5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories