audit

audit is a command for Claude Code from Kasempiternal/axiom-v2. It costs 11 tokens per session (885 once invoked), scanned A, original, MIT.

A command that examines an iOS project and selects focused audits, such as checks for concurrency, memory, performance, navigation, or layout.

In plain words
What is it for?
Use it to request a specific audit area or get suggestions based on the project, including checks for Swift concurrency, retain cycles, database schemas, SwiftUI performance, and deep links.
Why use it?
It helps decide which parts of a project need review instead of requiring you to know the available audit tools first.

Command for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the axiom plugin — 40 skills, 8 commands, 12 agents, 2 hooks shipped together

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 commands/kasempiternal/axiom-v2/audit
Clone the repo
git clone --depth 1 https://github.com/Kasempiternal/axiom-v2

Made for: Claude Code.

Or install axiom, the plugin that ships this one along with the rest of its 40 skills, 8 commands, 12 agents, 2 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 audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/kasempiternal/axiom-v2/audit.svg)](https://agentmods.dev/commands/kasempiternal/axiom-v2/audit)
Your own site
<a href="https://agentmods.dev/commands/kasempiternal/axiom-v2/audit"><img src="https://agentmods.dev/badge/commands/kasempiternal/axiom-v2/audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 885 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 5.1 $0.00011 $0.00885
Opus 5 $0.00005 $0.00443
Sonnet 5 $0.00002 $0.00177
Haiku 4.5 $0.00001 $0.00089

Measured 5d ago against content hash cb6a220b287b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

audit 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.

axiom-plugin/commands/audit.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an iOS project auditor with access to specialized Axiom v2 audit agents.

Your Task

If user specified an area -> launch that specific audit agent If no area specified -> analyze project and suggest relevant audits

Available Audits

Code Auditor (code-auditor agent)

Area --focus Detects
concurrency concurrency Swift 6 data races, unsafe Task captures, actor isolation
memory memory Retain cycles, leaks, Timer/observer patterns
performance performance ARC issues, allocation patterns, generic specialization
codable codable JSON serialization issues, Codable anti-patterns
schema schema Unsafe migrations, DROP operations, FK issues

UI Auditor (ui-auditor agent)

Area --focus Detects
architecture architecture Logic in view, MVVM patterns, boundary violations
swiftui-performance performance Expensive body, formatters, missing lazy
navigation navigation NavigationStack issues, deep linking
layout layout GeometryReader misuse, hardcoded breakpoints
glass glass iOS 26 liquid glass adoption
text text TextKit issues, text rendering

Data Auditor (data-auditor agent)

Area --focus Detects
core-data core-data Thread safety, schema migrations, N+1 queries
swiftdata swiftdata @Model issues, VersionedSchema, relationships
icloud icloud NSFileCoordinator, entitlements, conflicts
storage storage File protection, storage strategies

Standalone Agents

Area Agent Detects
security / privacy security-scanner API keys, Privacy Manifests, ATS
energy energy-auditor Timer abuse, polling, location, animation leaks
accessibility accessibility-auditor VoiceOver, Dynamic Type, WCAG
modernization modernizer ObservableObject->@Observable, deprecated APIs
camera modernizer (camera) Deprecated capture APIs, threading
networking modernizer (networking) SCNetworkReachability, deprecated patterns
spritekit modernizer (spritekit) Physics bitmasks, node accumulation
testing test-runner (audit mode) Flaky tests, slow tests, Swift Testing migration

Read the full file on GitHub · 84 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 · 84 lines · 11 tokens per session scan A cb6a220b287b

Subscribe to this mod's changes

audit is a command published in the GitHub repository Kasempiternal/axiom-v2 (4 stars, last pushed 6mo ago), licensed MIT. It adds 11 tokens to every session and 885 once invoked, about $0.0001 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.