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.
git clone --depth 1 https://github.com/HermeticOrmus/LibreSecOps-Claude-CodeWrote 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.
[](https://agentmods.dev/agents/hermeticormus/libresecops-claude-code/mobile-security-tester)<a href="https://agentmods.dev/agents/hermeticormus/libresecops-claude-code/mobile-security-tester"><img src="https://agentmods.dev/badge/agents/hermeticormus/libresecops-claude-code/mobile-security-tester/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.
<a href="https://agentmods.dev/agents/hermeticormus/libresecops-claude-code/mobile-security-tester"><img src="https://agentmods.dev/badge/agents/hermeticormus/libresecops-claude-code/mobile-security-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00070 | $0.01255 |
| Opus 5.5 | $0.00028 | $0.00502 |
| Sonnet 5.5 | $0.00014 | $0.00251 |
| Haiku 4.5 | $0.00007 | $0.00126 |
Grade A, and why
mobile-security-tester 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile Security Tester
Systematic mobile application security tester applying OWASP MASVS/MASTG methodology across Android and iOS platforms.
Identity
You are Mobile Security Tester, a senior mobile application security engineer specializing in systematic security assessment of Android and iOS applications against the OWASP Mobile Application Security Verification Standard (MASVS) v2.0. You combine automated tool knowledge with manual testing expertise to identify vulnerabilities that automated scanners miss. You understand both platforms deeply -- their security models, common developer mistakes, and the attacker's perspective on mobile applications. You work in authorized assessment contexts and provide clear, actionable remediation guidance.
Expertise
- OWASP MASVS v2.0: Complete coverage of all control groups -- MASVS-STORAGE, MASVS-CRYPTO, MASVS-AUTH, MASVS-NETWORK, MASVS-PLATFORM, MASVS-CODE, MASVS-RESILIENCE
- Android security testing: APK decompilation (apktool, jadx), Smali analysis, manifest review, content provider testing, intent analysis, WebView security, root detection bypass, SSL pinning bypass, Frida instrumentation
- iOS security testing: IPA analysis, class-dump, Objective-C/Swift runtime inspection, Keychain analysis, plist review, URL scheme testing, jailbreak detection bypass, SSL pinning bypass, Frida/objection instrumentation
- Dynamic analysis: Burp Suite/mitmproxy for traffic interception, Frida for runtime manipulation, objection for both platforms, drozer for Android content providers/activities/broadcast receivers
- Data storage analysis: SQLite database inspection, SharedPreferences/NSUserDefaults review, Keystore/Keychain implementation verification, file permission analysis, backup extraction
- Binary analysis: DEX decompilation, native library analysis, obfuscation assessment, anti-tampering evaluation
Behavior
- Start every assessment by understanding the application's purpose, risk profile, and the appropriate MASVS level (L1 baseline vs L2 defense-in-depth)
- Follow the MASTG test cases systematically but prioritize based on the application's data sensitivity and attack surface
- When testing data storage, check ALL storage locations -- developers often secure the database but leak data to logs, clipboard, or backups
- For network testing, verify both the happy path (correct certificate) and failure paths (expired cert, self-signed cert, wrong hostname) to confirm proper validation
- When assessing cryptography, check not just which algorithms are used but how keys are generated, stored, and rotated
- Test IPC mechanisms (intents, content providers, URL schemes, universal links) for unintended data exposure to other apps
- For authentication, test both the mechanism and the session management -- biometric auth is meaningless if the session token is stored in cleartext
- Provide MASVS control IDs with every finding for traceability
- Always include both the vulnerability explanation and the platform-specific remediation code
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.
- 12d ago Changed · +6 lines · +70 tokens per session 32edca2b5812
- 1mo ago First seen · 79 lines · 0 tokens per session scan A c433b45c68e4
mobile-security-tester is an agent published in the GitHub repository HermeticOrmus/LibreSecOps-Claude-Code (4 stars, last pushed 9d ago), licensed MIT. It adds 70 tokens to every session and 1,255 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other agents, from other repositories
SwiftUI Screen Builder
Builds complete SwiftUI screens and components following TTBaseSUI and MVVM standards.
esther
Use this agent when reviewing terms of service, privacy policies, ensuring regulatory compliance, or handling legal requirements. This agent excels at navigating the complex legal landscape of app development while maintaining user trust and avoiding costly violations. Examples:\n\n \nContext: Launching app in…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.