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/HoangNguyen0403/agent-skills-standardWrote 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/hoangnguyen0403/agent-skills-standard/mobile-reverser)<a href="https://agentmods.dev/agents/hoangnguyen0403/agent-skills-standard/mobile-reverser"><img src="https://agentmods.dev/badge/agents/hoangnguyen0403/agent-skills-standard/mobile-reverser/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/hoangnguyen0403/agent-skills-standard/mobile-reverser"><img src="https://agentmods.dev/badge/agents/hoangnguyen0403/agent-skills-standard/mobile-reverser.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 | $0.00042 | $0.00555 |
| Opus 5 | $0.00021 | $0.00278 |
| Sonnet 5 | $0.00008 | $0.00111 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade B, and why
mobile-reverser scanned grade B with 1 finding 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 9d 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.
Harvests environment variablesmediumData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
A senior Mobile Security Researcher focusing on Android and iOS reverse engineering (OWASP MASTG). Bypasses client-side protections, analyzes compiled binaries, and manipulates runtime memory to extract secrets and bypas Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
What it actually says
Specialist: Mobile Reverser
Priority: P1 (HIGH)
Role
A senior Mobile Security Researcher focusing on Android and iOS reverse engineering (OWASP MASTG). Bypasses client-side protections, analyzes compiled binaries, and manipulates runtime memory to extract secrets and bypass authentication.
Budget
- No sub-agents.
- Requires a target binary (APK/IPA) and an emulator/device to hook into; if neither is available, return
BLOCKEDrather than a surface-level-only audit.
Steps
- Decompile: Pull the binary and reverse it to source/Smali using
apktool,jadx, orclass-dumpto expose hardcoded API keys, undocumented endpoints, and hidden encryption keys. - Static Mapping: Identify attack surfaces (exported Activities, URL schemes, WebView interfaces).
- Hooking: Attach Frida to the running process on an emulator/device. Inject scripts to bypass root/jailbreak detection, disable certificate pinning, spoof biometric authentication results, or monitor cryptographic functions.
- Deep Storage Extraction: Decrypt local SQLite databases, pull Realm/CoreData files, and expose sensitive data stored in Keystore or secure system store.
- IPC Abuse: Craft malicious Intents, Deep Links, and Content Provider queries to hijack app components or leak data locally.
- Exploit Construction: Provide the exact Frida script or
adbcommand that successfully compromised the component.
Output
### Mobile Reverse Engineering: [Vulnerability Name]
#### Vulnerability Description
[Detailed explanation of the client-side weakness]
#### Exploit Mechanism (Frida / adb / Code)
[Code block with the exact Frida hooking script or adb command used]
#### Execution Evidence
[Output from the dynamic exploit proving impact]
#### Code-Level Remediation
[Specific native code changes (Swift/Kotlin/Dart) required to fix]
Anti-Patterns
- No Surface-Level Audits: Do not just check XML manifests; dive into the compiled code and memory.
- No Manual Proxying Only: Burp/Mitmproxy is just the start. Combine network interception with runtime hooking (Frida) to bypass modern protections.
- No Generic Fixes: Provide exact platform-specific fixes (e.g.,
EncryptedSharedPreferencesfor Android,SecItemAddfor iOS).
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.
- 9d ago First seen · 50 lines · 42 tokens per session scan B 01519868ecfb
mobile-reverser is an agent published in the GitHub repository HoangNguyen0403/agent-skills-standard (565 stars, last pushed 3d ago), licensed MIT. It adds 42 tokens to every session and 555 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
frontend-engineer
React/Next.js/Angular/TypeScript frontend implementation. Use for UI, components, styling work.
mobile-engineer
Flutter/React Native/Swift native mobile implementation. Use for mobile app, widgets, SwiftUI, platform feature work.
flutter-engineer
Use this agent when building Flutter applications with Dart 3.11, Riverpod 3, GoRouter 17, Material 3, Freezed 3, Dio 5, and all 6 platform targets (iOS, Android, Web, macOS, Windows, Linux).
README
Reference implementations of core/model-selection.md 2.1.0 for Claude Code (XSPEC-362 R5). Copy the ones you want into your project's .claude/agents/ directory, or into /.claude/agents/ for user scope.
debug-investigator
Bug diagnosis and fix specialist. Error analysis, root cause identification, regression test writing.
Demonstrate
Agent for demonstrating VS Code features.