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 plugins/incogbyte/android-reverse-engineering-claude-skill/marketplace/plugin marketplace add incogbyte/android-reverse-engineering-claude-skillgit clone --depth 1 https://github.com/incogbyte/android-reverse-engineering-claude-skillGrade A, and why
android-reverse-engineering-claude-skill 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 yesterday.
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.
What it actually says
{
"name": "android-reverse-engineering-claude-skill",
"owner": {
"name": "incogbyte",
"url": "https://github.com/incogbyte"
},
"metadata": {
"description": "Marketplace for the Android Reverse Engineering Claude Code plugin.",
"version": "1.0.0"
},
"plugins": [
{
"name": "android-reverse-engineering",
"source": "./plugins/android-reverse-engineering",
"description": "Decompile Android APK/XAPK/AAB/DEX/JAR/AAR with jadx or Vineflower, extract HTTP APIs, trace call flows, audit security, and run adaptive Frida dynamic analysis.",
"version": "1.0.0",
"author": {
"name": "incogbyte",
"url": "https://github.com/incogbyte"
},
"homepage": "https://github.com/incogbyte/android-reverse-engineering-claude-skill",
"repository": "https://github.com/incogbyte/android-reverse-engineering-claude-skill",
"license": "Apache-2.0",
"keywords": [
"android",
"reverse-engineering",
"apk",
"jadx",
"decompile",
"api-extraction",
"frida",
"security"
]
}
]
}
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.
- yesterday First seen · 37 lines scan A 90c51b11aacd
android-reverse-engineering-claude-skill is a plugin published in the GitHub repository incogbyte/android-reverse-engineering-claude-skill (108 stars, last pushed 2mo ago), licensed Unlicense. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
salingnh-reverse-tools
Safe Android Reverser MCP for sandboxed, capability-aware Android reverse engineering.
safe-android-reverser
Sandboxed Android reverse engineering with semantic program indexing, XREF/CFG queries and structured network evidence through MCP.
android-reverse-engineering-skill
Claude Code plugins for Android reverse engineering.
android-reverse-engineering
Decompile Android APK/JAR/AAR with jadx, trace call flows through libraries, and document extracted APIs.
cometchat
Plugin marketplace listing 1 plugin: cometchat.
compose-doctor
Plugin marketplace listing 1 plugin: compose-doctor.