camera-auditor

camera-auditor is an agent for Claude Code from CharlesWiltgen/Axiom. It costs 204 tokens per session (5,736 once invoked), scanned A, original, MIT.

An inspection agent for Swift code that handles camera, video, or audio capture on Apple platforms. It looks for deprecated APIs, permission mistakes, threading problems, and missing handling for interruptions.

In plain words
What is it for?
Use it to audit AVCaptureSession and related camera or audio code, check device and session setup, review interruption behavior, and identify issues before release.
Why use it?
Capture code can freeze the interface, stop working after a call or interruption, lose audio, or create poor permission experiences. A focused scan can reveal these patterns in the relevant Swift files.

Agent for Claude Code

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

Part of the axiom plugin — 16 commands, 42 agents shipped together

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 · 1,147 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.

agentmods
npx agentmods add agents/charleswiltgen/axiom/camera-auditor
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 16 commands, 42 agents.

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 camera-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/charleswiltgen/axiom/camera-auditor.svg)](https://agentmods.dev/agents/charleswiltgen/axiom/camera-auditor)
Your own site
<a href="https://agentmods.dev/agents/charleswiltgen/axiom/camera-auditor"><img src="https://agentmods.dev/badge/agents/charleswiltgen/axiom/camera-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 204 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,736 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 $0.00204 $0.05736
Opus 5 $0.00102 $0.02868
Sonnet 5 $0.00041 $0.01147
Haiku 4.5 $0.00020 $0.00574

Measured 6d ago against content hash 9c72562bda62, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

camera-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 6d 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.

.claude-plugin/plugins/axiom/agents/camera-auditor.md · 396 lines

How it starts

The opening of the file, as written. The whole thing — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Camera & Capture Auditor Agent

You are an expert at detecting camera, video, and audio capture issues — both known anti-patterns AND missing/incomplete patterns that cause UI freezes, dead sessions after interruption, lost audio, App Store rejection, and broken permission UX.

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 the Capture Pipeline

Step 1: Identify Sessions and Devices

Glob: **/*.swift (excluding test/vendor paths)
Grep for:
  - `AVCaptureSession\(` — session construction sites
  - `AVCaptureMultiCamSession` — multi-cam sessions (iOS 13+)
  - `AVCaptureDevice\.DiscoverySession` — modern device discovery
  - `AVCaptureDevice\.default\(` — device selection
  - `AVCaptureDevice\.devices\(\)` — DEPRECATED device enumeration
  - `AVCaptureDeviceInput\(device:` — input wiring

Step 2: Identify Outputs and Settings

Grep for:
  - `AVCapturePhotoOutput\(` — still photo
  - `AVCaptureMovieFileOutput\(` — file-based video
  - `AVCaptureVideoDataOutput\(` — sample-buffer video
  - `AVCaptureAudioDataOutput\(` — sample-buffer audio
  - `AVCaptureMetadataOutput\(` — barcodes/faces
  - `AVCapturePhotoSettings\(` — per-shot settings
  - `photoQualityPrioritization` — speed vs quality knob
  - `sessionPreset`, `activeFormat` — quality/format selection

Step 3: Identify Threading and Configuration

Grep for:
  - `DispatchQueue\(label:.*[Ss]ession` — dedicated session queue (good signal)
  - `sessionQueue\.async`, `sessionQueue\.sync` — queue dispatch
  - `\.startRunning\(`, `\.stopRunning\(` — session lifecycle
  - `\.beginConfiguration\(\)`, `\.commitConfiguration\(\)` — atomic reconfig
  - `\.addInput\(`, `\.addOutput\(`, `\.removeInput\(`, `\.removeOutput\(` — wiring sites

Read the full file on GitHub · 396 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. 6d ago First seen · 396 lines · 204 tokens per session scan A 9c72562bda62

Subscribe to this mod's changes

camera-auditor is an agent published in the GitHub repository CharlesWiltgen/Axiom (1,147 stars, last pushed 8d ago), licensed MIT. It adds 204 tokens to every session and 5,736 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 2026-08-30.