Agentic binary reverse engineering for ELF binaries on ARM64, ARMv7, x86_64. Combines static analysis (radare2, Ghidra) with dynamic tracing (QEMU, GDB, Frida) in a hypothesis-driven workflow, then compiles findings into structured reports with evidence chains.
Use when you need to run a binary, trace execution, or observe runtime behavior. Runtime analysis via QEMU emulation, GDB debugging, and Frida hooking - syscall tracing (strace), breakpoints, memory inspection, function interception. Keywords - "run binary", "execute", "debug", "trace syscalls", "set breakpoint", "qemu", "gdb", "frida", "strace", "watch memory"
Use when analyzing binary structure, disassembling code, or decompiling functions. Deep static analysis via radare2 (r2) and Ghidra headless - function enumeration, cross-references (xrefs), decompilation, control flow graphs. Keywords - "disassemble", "decompile", "what does this function do", "find functions", "analyze code", "r2", "ghidra", "pdg", "afl"
Use when ready to document findings, generate a report, or summarize binary analysis results. Compiles analysis findings into structured reports - correlates facts from triage/static/dynamic phases, validates hypotheses, generates documentation with evidence chains. Keywords - "summarize findings", "generate report", "document analysis", "what did we find", "write up results", "export findings"
Use when reverse engineering tools are missing, not working, or need configuration. Installation guides for radare2 (r2), Ghidra, GDB, QEMU, Frida, binutils, and cross-compilation toolchains. Keywords - "install radare2", "setup ghidra", "r2 not found", "qemu missing", "tool not installed", "configure gdb", "cross-compiler"
Use when first encountering an unknown binary, ELF file, executable, or firmware blob. Fast fingerprinting via rabin2 - architecture detection (ARM, x86, MIPS), ABI identification, dependency mapping, string extraction. Keywords - "what is this binary", "identify architecture", "check file type", "rabin2", "file analysis", "quick scan"
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
You pulled a binary off an embedded device. It's an ELF, probably ARM, and you need to figure out what it does. Binary RE gives Claude the tools to help — radare2 for disassembly, Ghidra for decompilation, GDB for dynamic analysis, QEMU for emulation — driven by hypothesis-testing, not blind exploration.
/plugin marketplace add 2389-research/claude-plugins
/plugin install binary-re@2389-research
binary-re -- structured RE workflow with hypothesis-driven analysisUser: "Analyze this binary from an IoT device - ARM, Linux-based"
Claude: [Triggers binary-re skill]
Let me start with triage to understand what we're working with.
Phase 1: Initial Triage
┌─────────────────────────────────────────┐
│ Architecture: ARM 32-bit LE (v7) │
│ Libc: musl 1.2.3 │
│ Dependencies: libcurl, libssl, libz │
│ Stripped: Yes │
│ Strings: 847 (including URLs, paths) │
└─────────────────────────────────────────┘
FACTS recorded:
- Links against libcurl.so.4 (network client)
- Contains string "api.vendor.com/telemetry"
- Imports socket, connect, SSL_read functions
HYPOTHESIS: This is a telemetry client that phones home over HTTPS
Confidence: 0.7
Evidence: curl+ssl imports, telemetry URL string
Do you want me to proceed with static analysis of network-related
functions, or should we try dynamic analysis under QEMU first?
# Required
sudo apt install radare2 qemu-user gdb-multiarch
# Recommended
# Ghidra from https://ghidra-sre.org/
pip install frida-tools
# ARM sysroots
sudo apt install libc6-armhf-cross libc6-arm64-cross
The LLM drives analysis; the human provides context.
You tell Claude what platform/device the binary came from, what hardware is involved, what the binary is theorized to do, and any constraints (no network, isolated test env, etc).
Claude runs the tools, forms hypotheses from evidence, designs experiments to test theories, and synthesizes findings into something actionable.
The skill asks for confirmation before:
If Binary RE helped you crack a firmware blob, a ⭐ helps us know it's landing.
Built by 2389 · Part of the Claude Code plugin marketplace
npx claudepluginhub 2389-research/claude-plugins --plugin binary-reMCP server for agent social media platform - enables AI agents to interact in team-based discussions
Iterative artifact refinement with investigation-first judge board - constructs problem-specific judges that read the code, understand the problem, and propose evidence-based improvements
Tiered-delegation execution where Sonnet plans a spec into sprints, a cheap Haiku agent builds and self-verifies against the gate, and a scoped Sonnet fix runs only on failure - benchmarked ~64% cheaper than Opus at equal quality.
A comprehensive MCP server that provides Claude with private journaling, semantic search, resources, and guided prompts for reflection and learning
Dispatch panels of specialized subagents to review projects — expert audits, first-impression personas, task-completion flows, and pedantic nitpicks
Binary reverse engineering, malware analysis, firmware security, and software protection research for authorized security research, CTF competitions, and defensive security
Reverse engineer binaries using Ghidra's headless analyzer. Decompile executables, extract functions, strings, symbols, and analyze call graphs without GUI.
Analyze binaries using angr's Python framework. Decompile, recover control flow graphs, find vulnerabilities via symbolic execution, and extract symbols from stripped binaries.
Binary analysis skills for VulHunt MCP - decompilation, dataflow analysis, pattern matching, and more
AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.
Claude Code skills for x64dbg debugger automation — state snapshots, memory analysis, and more