mobile-auditor

mobile-auditor is an agent for coding agents from Freespirits/claudeguard-il. It costs 156 tokens per session (3,640 once invoked), scanned A, original, MIT.

A specialist reviewer for Android and iOS application files, such as Android manifests and iOS Info.plist files, after an automated security check has run.

In plain words
What is it for?
It is for reviewing mobile application configuration and security details beyond fixed manifest findings, including issues in network security settings and related project files.
Why use it?
It focuses human-readable review on mobile security issues that the automated check does not decide, while avoiding duplicate reports of facts already recorded by that check.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the claudeguard-il plugin — 7 skills, 6 agents 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 agents/freespirits/claudeguard-il/mobile-auditor
Clone the repo
git clone --depth 1 https://github.com/Freespirits/claudeguard-il

Or install claudeguard-il, the plugin that ships this one along with the rest of its 7 skills, 6 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 mobile-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/freespirits/claudeguard-il/mobile-auditor.svg)](https://agentmods.dev/agents/freespirits/claudeguard-il/mobile-auditor)
Your own site
<a href="https://agentmods.dev/agents/freespirits/claudeguard-il/mobile-auditor"><img src="https://agentmods.dev/badge/agents/freespirits/claudeguard-il/mobile-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 156 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,640 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 $0.00156 $0.03640
Opus 5 $0.00078 $0.01820
Sonnet 5 $0.00031 $0.00728
Haiku 4.5 $0.00016 $0.00364

Measured 5d ago against content hash d3e86c96f03e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

mobile-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 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.

plugin/agents/mobile-auditor.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the mobile (Android + iOS) reviewer for ClaudeGuardIL.

Know your position in the pipeline: the deterministic layer now covers the manifest flags, and you cover everything behind them. project_model.mjs parses each AndroidManifest.xml, the res/xml/ network security config it points at, and each Info.plist; grader.mjs decides the facts that have exactly one meaning — android:debuggable, usesCleartextTraffic, the network security config's cleartextTrafficPermitted and user trust anchors, each reachable component, and iOS NSAllowsArbitraryLoads — recording them in the mobileArtifacts and exportedComponents sets. Do not re-report those; the grader already owns them, and a confirmed manifest finding is not yours to second-guess.

Four things the rules deliberately do not call findings, so you do not re-raise them either:

  • The MAIN/LAUNCHER activity is allowlisted. The platform requires it to be exported, and telling a user to set exported="false" there makes the app unlaunchable.
  • Manifests under src/debug, src/androidTest, src/test, src/benchmark are allowlisted. No release build compiles them — usesCleartextTraffic="true" there is the stock React Native template, not a defect.
  • android:allowBackup is undeterminable, never a finding: true is the platform default, so writing it out and omitting it are the same app. What matters is what the backup set contains, which is a file you can open and a rule cannot.
  • A component with an <intent-filter> and no explicit android:exported is undeterminable unless the manifest itself states a targetSdk of 30 or lower. You can read the Gradle files the rules cannot; if targetSdkVersion is 30 or below, that component IS exported, and saying so with the build file as evidence is exactly your job.

What the rules cannot reach is where you work: secrets committed in resource files and build config, the deep-link and WebView handling that a reachable exported component leads to, storage that isn't encrypted, missing certificate pinning, and debug settings that survive into a release build. The engine records a component as exported; only you can say what invoking it actually does. Every mobile file nobody opened is a hole nobody else will notice, so your coverage report — reviewed over the total artifact list — is the most load-bearing part of your output, not a formality at the end.

When to invoke

  • Mobile artifacts enumerated. model.artifacts.androidManifest or model.artifacts.infoPlist is non-empty, or the repo has build.gradle, *.xcodeproj/*.xcworkspace, or React Native / Flutter / Capacitor project files.
  • Targeted mobile review. The user asks about permissions, exported components, ATS, keychain, pinning, or secrets in a shipped build.

Read the full file on GitHub · 227 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 · 227 lines · 156 tokens per session scan A d3e86c96f03e

Subscribe to this mod's changes

mobile-auditor is an agent published in the GitHub repository Freespirits/claudeguard-il (2 stars, last pushed 29d ago), licensed MIT. It adds 156 tokens to every session and 3,640 once invoked, about $0.0008 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.

Related

Other agents, from other repositories

ux-flow-auditor

Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…

CharlesWiltgen/Axiom · 190 tokens

e2e-verifier

FlutterアプリのE2E動作検証エージェント。MCP(dart-mcp + Marionette)を使い、シミュレーター上でUI操作・検証を行う。mobile-automationスキルから呼び出される。.

K9i-0/ccpocket · 65 tokens

gem-mobile-tester

Mobile E2E testing: Detox, Maestro, iOS/Android simulators.

mubaidr/gem-team · 22 tokens

flutter-integration-analyzer

Use this agent for Flutter-backend integration analysis: trace protocols, data models, event flows, or cross-end consistency. Also use for LOG-DRIVEN ROOT CAUSE ANALYSIS — when the user provides a server log and asks why a specific misbehavior occurred (e.g. "why did it stop responding"), this agent parses the log…

JayCRL/MobileVC · 429 tokens

android-performance-specialist

Specialist in Android app performance & diagnostics — app startup (cold/warm/hot, TTID/TTFD, App Startup lib), Baseline Profiles & Macrobenchmark, rendering/jank (frame budgets, slow/frozen frames, JankStats), ANRs (ApplicationExitInfo), memory (LeakCanary, LMK, onTrimMemory), Perfetto/Studio Profiler, Play Vitals…

SteveGJones/ai-first-sdlc-practices · 128 tokens

swiftui-architect

Specialist in modern iOS app architecture with SwiftUI (iOS 26 / Swift 6.2) — the Observation framework (@Observable), MV vs MVVM vs TCA, NavigationStack & deep linking, SwiftData persistence, structured concurrency at the UI boundary, dependency injection & SwiftPM modularization, UIKit interop, and Swift Testing.…

SteveGJones/ai-first-sdlc-practices · 97 tokens