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.
npx agentmods add skills/theqmaks/areclaw-plugin/android-securitynpx skills add TheQmaks/areclaw-plugin --skill android-securitygit clone --depth 1 https://github.com/TheQmaks/areclaw-pluginWhat 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 | $0.00091 | $0.09224 |
| Opus 5 | $0.00046 | $0.04612 |
| Sonnet 5 | $0.00018 | $0.01845 |
| Haiku 4.5 | $0.00009 | $0.00922 |
Grade A, and why
android-security scanned grade A with 2 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 2d 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
adb shell chmod 755 /data/local/tmp/<NAME>-server Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl https://<project-id>.firebaseio.com/.json How it starts
The opening of the file, as written. The whole thing — 897 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Android Security Analysis
Comprehensive Android application security analysis combining static reverse engineering, dynamic instrumentation, secret scanning, API mapping, and OWASP Mobile Top 10 assessment. This skill chains acquisition, reconnaissance, static analysis, dynamic analysis, API documentation, security assessment, and report generation into a single structured workflow.
Philosophy: Think, don't checklist. Every finding is a lead — a hardcoded API key means check where it's used and what access it grants. An exported Activity means launch it and test for abuse. A weak cipher means trace where it's used and what it protects. Chain of reasoning: finding, implication, verification, report.
Prerequisites
This skill requires a set of static and dynamic analysis tools. Run the dependency checker to verify the environment:
bash ${CLAUDE_PLUGIN_ROOT}/skills/android-security/scripts/check-deps.sh
Required Tools
| Tool | Purpose | Install Check |
|---|---|---|
| Java JDK 17+ | Runtime for most tools | java -version |
| jadx | DEX-to-Java decompiler | jadx --version |
| apktool | APK disassembly (smali + resources) | apktool --version |
| adb | Android device interaction | adb version |
| frida + frida-tools | Dynamic instrumentation | frida --version |
| apkid | Protection/packer detection | apkid --help |
| apkleaks | APK secret/URL scanning | pip show apkleaks |
Recommended Tools
| Tool | Purpose | Install Check |
|---|---|---|
| trufflehog | Deep secret scanning (800+ types, validates live credentials) | pip show trufflehog |
| objection | Runtime exploration (Frida-based) | objection --version |
| Ghidra | Native .so binary analysis | Check tools/ghidra/ |
| radare2 | CLI binary analysis | r2 -v |
| dex2jar | DEX-to-JAR conversion | d2j-dex2jar.sh --version |
| mitmproxy | Traffic interception | mitmdump --version |
| justapk | Multi-source APK downloader | pip show justapk |
What ships with it
28 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/frida-reference.md 19 KB
- references/mastg-mapping.md 17 KB
- references/mitre-attack-mapping.md 19 KB
- references/owasp-checklist.md 27 KB
- references/search-patterns.md 13 KB
- references/setup-guide.md 11 KB
- references/tool-reference.md 19 KB
- scripts/check-deps.sh 11 KB runs code
- scripts/frida/anti-frida-bypass.js 17 KB runs code
- scripts/frida/api-tracer.js 4.8 KB runs code
- scripts/frida/crypto-tracer.js 6.7 KB runs code
- scripts/frida/dex-loader-monitor.js 6.4 KB runs code
- scripts/frida/enum-classes.js 3.4 KB runs code
- scripts/frida/hook-template.js 4.2 KB runs code
- scripts/frida/http-logger.js 5.2 KB runs code
- scripts/frida/intent-monitor.js 6.4 KB runs code
- scripts/frida/reflection-tracer.js 7.8 KB runs code
- scripts/frida/root-bypass.js 7.1 KB runs code
- scripts/frida/shared-prefs-monitor.js 4.8 KB runs code
- scripts/frida/ssl-bypass.js 5.6 KB runs code
- scripts/frida/stacktrace-helper.js 9.2 KB runs code
- scripts/frida/stalker-tracer.js 6.3 KB runs code
- scripts/frida/webview-interceptor.js 23 KB runs code
- scripts/install-deps.py 27 KB runs code
- scripts/pytools/check_updates.py 16 KB runs code
- scripts/pytools/traffic_to_collection.py 11 KB runs code
- scripts/pytools/ui_explorer.py 18 KB runs code
- scripts/setup-env.sh 2.5 KB runs 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.
- 2d ago First seen · 897 lines · 91 tokens per session scan A b38493490ca4
android-security is a skill published in the GitHub repository TheQmaks/areclaw-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 91 tokens to every session and 9,224 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
edge-to-edge
Use this skill to migrate your Jetpack Compose app to add adaptive edge-to-edge support and troubleshoot common issues. Use this skill to fix UI components (like buttons or lists) that are obscured by or overlapping with the navigation bar or status bar, fix IME insets, and fix system bar legibility.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
flutter-fix-layout-issues
Fixes Flutter layout errors (overflows, unbounded constraints) using Dart and Flutter MCP tools. Use when addressing "RenderFlex overflowed", "Vertical viewport was given unbounded height", or similar layout issues.
referral-program
When the user wants to design, launch, or optimize an in-app referral / invite / share-to-earn program — including reward structure, mechanics, fraud prevention, deep link setup, and viral coefficient measurement. Use when the user mentions "referral program", "invite a friend", "refer and earn", "share to earn"…
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.
ios-hig-design
Design native iOS interfaces following Apple Human Interface Guidelines. Use when the user mentions "iPhone app", "iPad layout", "SwiftUI", "UIKit", "Dynamic Island", "safe areas", "HIG compliance", "SF Symbols", "haptic feedback", "iOS accessibility", "make my app feel native", or "follow Apple design guidelines".…