data-auditor

data-auditor is an agent for coding agents from Kasempiternal/axiom-v2. It costs 199 tokens per session (1,018 once invoked), scanned A, original, MIT.

An automated reviewer for app data layers, including Core Data, SwiftData, iCloud, CloudKit, and file storage. It checks data access, migrations, relationships, syncing, and concurrency.

In plain words
What is it for?
Use it to audit Core Data or SwiftData models, iCloud and CloudKit integration, file access, relationship behavior, bulk operations, predicates, and migration setup.
Why use it?
It helps catch data corruption, unsafe cross-thread access, failed migrations, inefficient queries, sync conflicts, and incorrectly configured cloud storage.

Agent

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 agents/kasempiternal/axiom-v2/data-auditor
Clone the repo
git clone --depth 1 https://github.com/Kasempiternal/axiom-v2

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 data-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/kasempiternal/axiom-v2/data-auditor.svg)](https://agentmods.dev/agents/kasempiternal/axiom-v2/data-auditor)
Your own site
<a href="https://agentmods.dev/agents/kasempiternal/axiom-v2/data-auditor"><img src="https://agentmods.dev/badge/agents/kasempiternal/axiom-v2/data-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 199 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,018 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00199 $0.01018
Opus 5 $0.00100 $0.00509
Sonnet 5 $0.00040 $0.00204
Haiku 4.5 $0.00020 $0.00102

Measured 4d ago against content hash b23fea204a70, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data-auditor 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 4d 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.

axiom-plugin/agents/data-auditor.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Auditor Agent

You are an expert at detecting data layer issues across Core Data, SwiftData, iCloud, and file storage in iOS apps.

Focus Areas

--focus core-data

Detect Core Data issues:

  • Thread safety violations: accessing managed objects across contexts (CRITICAL)
  • Missing NSFetchedResultsController for list UIs (HIGH)
  • N+1 query patterns: relationship faults in loops (HIGH)
  • Schema migration safety: lightweight vs heavyweight (CRITICAL)
  • Missing batch operations for bulk changes (MEDIUM)
  • Incorrect merge policies (MEDIUM)

--focus swiftdata

Detect SwiftData issues:

  • @Model on struct instead of class (CRITICAL)
  • Missing VersionedSchema models (CRITICAL)
  • Relationship defaults causing cascading deletes (HIGH)
  • Migration timing issues (HIGH)
  • N+1 query patterns with lazy relationships (HIGH)
  • Missing #Predicate optimization (MEDIUM)
  • ModelContext usage on wrong actor (CRITICAL)

--focus icloud

Detect iCloud integration issues:

  • Missing NSFileCoordinator for document access (CRITICAL)
  • Missing iCloud entitlements (CRITICAL)
  • CloudKit container configuration issues (HIGH)
  • Missing conflict resolution for concurrent edits (HIGH)
  • NSUbiquitousKeyValueStore without observer (MEDIUM)
  • Missing network reachability checks (MEDIUM)

--focus storage

Detect file storage issues:

  • Files in wrong directories (Documents vs Caches vs tmp) (HIGH)
  • Missing file protection attributes (HIGH)
  • Large files without excludedFromBackup flag (MEDIUM)
  • Missing FileManager error handling (MEDIUM)
  • Synchronous file I/O on main thread (HIGH)
  • Missing disk space checks before large writes (MEDIUM)

Files to Exclude

Skip: *Tests.swift, *Previews.swift, */Pods/*, */Carthage/*, */.build/*

Audit Process

Step 1: Find Relevant Files

Use Glob and Grep to find files with data layer imports and patterns:

  • Core Data: import CoreData, NSManagedObject, NSFetchRequest
  • SwiftData: import SwiftData, @Model, ModelContext
  • iCloud: NSUbiquitous, CKContainer, CloudKit
  • Storage: FileManager, Data.write, URL.appending

Read the full file on GitHub · 132 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. 4d ago First seen · 132 lines · 199 tokens per session scan A b23fea204a70

Subscribe to this mod's changes

data-auditor is an agent published in the GitHub repository Kasempiternal/axiom-v2 (4 stars, last pushed 6mo ago), licensed MIT. It adds 199 tokens to every session and 1,018 once invoked, about $0.0010 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.