reverse-engineer

A specialist workflow for examining compiled programs and developing exploits, including analysis with tools such as Ghidra, Radare2, GDB, and strace.

In plain words
What is it for?
It is for authorized binary reverse engineering, malware analysis, debugging, shellcode and ROP work, and capture-the-flag challenges.
Why use it?
It provides a structured way to understand a binary's behavior and document analysis while requiring authorization and an isolated environment for execution.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/mukul975/threatswarm/reverse-engineer
Clone the repo
git clone --depth 1 https://github.com/mukul975/Threatswarm

Made for: Claude Code.

Per session 106 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,086 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00106 $0.03086
Opus 5 $0.00053 $0.01543
Sonnet 5 $0.00021 $0.00617
Haiku 4.5 $0.00011 $0.00309

Measured 2d ago against content hash 03274a7ea866, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reverse-engineer 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 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.

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.

.claude/agents/reverse-engineer.md · 314 lines

How it starts

The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cybersecurity Skills (Invoke First)

Before starting binary reverse engineering, invoke these skills via the Skill tool:

  • cybersecurity-skills:performing-binary-exploitation-analysis
  • cybersecurity-skills:reverse-engineering-malware-with-ghidra
  • cybersecurity-skills:reverse-engineering-dotnet-malware-with-dnspy
  • cybersecurity-skills:analyzing-heap-spray-exploitation
  • cybersecurity-skills:reverse-engineering-rust-malware
  • cybersecurity-skills:analyzing-golang-malware-with-ghidra
  • cybersecurity-skills:reverse-engineering-ransomware-encryption-routine
  • cybersecurity-skills:analyzing-packed-malware-with-upx-unpacker

Scope Enforcement

Verify binary target is from an authorized engagement listed in scope.txt. Dynamic analysis (execution) requires isolated environment — use VM or Docker. Document hash of binary before analysis to ensure integrity.

Binary Triage

mkdir -p evidence/$(date +%Y%m%d)/$TARGET/re/{static,dynamic,exploits,dumps}

# Identify binary type
file $BINARY 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/re/static/file_type.txt
sha256sum $BINARY | tee evidence/$(date +%Y%m%d)/$TARGET/re/static/sha256.txt
md5sum $BINARY

# Security mitigations check
checksec --file=$BINARY 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/re/static/checksec.txt
# Output: NX, Canary, RELRO, PIE, ASLR flags

# Library dependencies
ldd $BINARY 2>/dev/null | tee evidence/$(date +%Y%m%d)/$TARGET/re/static/libraries.txt
readelf -d $BINARY | grep NEEDED 2>/dev/null

# Symbols
nm $BINARY 2>/dev/null | tee evidence/$(date +%Y%m%d)/$TARGET/re/static/symbols.txt
nm $BINARY 2>/dev/null | grep -i "vuln\|win\|flag\|secret\|shell" || true

# Packing/obfuscation detection
upx -t $BINARY 2>/dev/null && echo "[!] UPX packed" || echo "Not UPX packed"
binwalk -E $BINARY 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/re/static/entropy.txt

# Extract strings
strings -n 6 $BINARY 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/re/static/strings.txt
strings -n 6 $BINARY | grep -iE "http|flag|password|secret|key|admin|cmd|system|exec" | \
  tee evidence/$(date +%Y%m%d)/$TARGET/re/static/interesting_strings.txt

# Section headers
readelf -S $BINARY 2>/dev/null | tee evidence/$(date +%Y%m%d)/$TARGET/re/static/sections.txt
objdump -d -M intel $BINARY 2>/dev/null | head -200 | \
  tee evidence/$(date +%Y%m%d)/$TARGET/re/static/disasm_head.txt

Read the full file on GitHub · 314 lines

Changes

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.

  1. 2d ago First seen · 314 lines · 0 tokens per session scan A 03274a7ea866

Subscribe to this mod's changes

reverse-engineer is an agent published in the GitHub repository mukul975/Threatswarm (77 stars, last pushed 4mo ago), licensed MIT. It adds 106 tokens to every session and 3,086 once invoked, about $0.0005 per session on Opus 5. 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.

Related

Other agents, from other repositories

autopilot

Autonomous hunt loop agent. Runs the full hunt cycle (scope → recon → rank → hunt → validate → report) without stopping for approval at each step. Configurable checkpoints (--paranoid, --normal, --yolo). Uses scopechecker.py for deterministic scope safety on every outbound request. Logs all requests to audit.jsonl.…

Awarexone/Agentic-Bug-Hunter · 84 tokens

token-auditor

Fast meme coin and token security auditor. Checks 8 token-specific bug classes (hidden mint, honeypot, fee manipulation, LP lock bypass, bonding curve exploits, authority retention, fake renounce, sandwich/MEV amplification). Runs tokenscanner.py for automated red flag detection. Covers EVM (Solidity) and Solana…

Awarexone/Agentic-Bug-Hunter · 97 tokens

report-writer

Bug bounty report writer. Generates professional H1/Bugcrowd/Intigriti/Immunefi reports. Impact-first writing, human tone, no theoretical language, CVSS 4.0 calculation included. Use after a finding has passed the 7-Question Gate and 4 validation gates. Never generates reports with "could potentially" language.

Awarexone/Agentic-Bug-Hunter · 75 tokens

validator

Finding validator. Runs the 7-Question Gate and 4-gate checklist on a described finding. Kills weak/theoretical findings fast before report writing. Prevents N/A submissions. Use before writing any report — describe the finding and this agent decides PASS, KILL, or DOWNGRADE with explanation.

Awarexone/Agentic-Bug-Hunter · 64 tokens

web3-auditor

Smart contract security auditor. Checks 10 bug classes in order of frequency (accounting desync 28%, access control 19%, incomplete path 17%, off-by-one 22% of Highs, oracle errors, ERC4626 attacks, reentrancy, flash loan oracle manipulation, signature replay, proxy/upgrade issues). Applies pre-dive kill signals…

Awarexone/Agentic-Bug-Hunter · 101 tokens

recon-agent

Subdomain enumeration and live host discovery specialist. Runs Chaos API (ProjectDiscovery), subfinder, assetfinder, dnsx, httpx, katana, waybackurls, gau, and nuclei. Produces prioritized attack surface for a target. Use when starting recon on a new target domain.

Awarexone/Agentic-Bug-Hunter · 63 tokens