rea vs reverse-skill
Reverse Engineer Anything: one MCP server plus CLI giving coding agents evidence-backed analysis of native binaries, JS/Electron apps, .NET assemblies and websites via Hopper, Ghidra or IDA. — versus — Reverse-engineering and pentest skill router for coding agents: routes APK/ELF/JS/PCAP/CTF tasks to the right playbook, bootstraps jadx/Frida/IDA-class toolchains, evolves a knowledge base. CN/EN.
Both turn a coding agent into a reverse engineer; reverse-skill routes to playbooks, REA ships an MCP tool layer over Ghidra/Hopper/IDA with evidence.
| rea | reverse-skill | |
|---|---|---|
| Stars | 434k | 44k |
| Forks | 108k | 6.6k |
| Language | TypeScript | PowerShell |
| License | MIT | MIT |
| Last activity | yesterday | 1 months ago |
| Topics | security, code-intel | security, skills |
| Curated connections | 3 | 4 |
rea — the curator's take
Use it when you want an agent to explain how a closed-source app or binary actually works, with cited evidence, using the disassembler you already own. Skip it for plain source-code understanding (a code-intel MCP is lighter) and mind legal/ToS limits on what you reverse; setup edits agent configs, so review the proposed changes.
reverse-skill — the curator's take
The router is the substance: agents don't know whether a task wants jadx, Frida or Burp, and this encodes that judgment — plus scope and authorization contracts BEFORE any target is touched, which most offensive-skill packs skip. When NOT: it's methodology, not tools — you still install the toolchain and hold the authorization it assumes; PowerShell-first heritage shows off-Windows; and the star count partly rides the CN security community wave.