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/jessefmoore/offensive-claude-code/reverse-engineeringnpx skills add jessefmoore/offensive-claude-code --skill reverse-engineeringgit clone --depth 1 https://github.com/jessefmoore/offensive-claude-codeWhat 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 | $0.00030 | $0.01461 |
| Opus 5 | $0.00015 | $0.00731 |
| Sonnet 5 | $0.00006 | $0.00292 |
| Haiku 4.5 | $0.00003 | $0.00146 |
Grade B, and why
reverse-engineering scanned grade B with 1 finding 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.
Reaches for credential filesmediumPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
# - /etc/shadow, /etc/passwd (hardcoded creds) Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reverse Engineering
When to Activate
- Analyzing compiled binaries for vulnerabilities
- Understanding proprietary protocols or file formats
- Malware analysis and unpacking
- Firmware extraction and analysis
- Bypassing anti-debugging/anti-tampering protections
- CTF binary challenges
- Patch diffing to find 1-day vulnerabilities
Static Analysis
Initial Triage
# File identification
file target_binary
rabin2 -I target_binary # binary info (arch, bits, endian, protections)
# Strings extraction
strings -n 8 target_binary | grep -iE '(password|key|secret|flag|http|/bin)'
rabin2 -z target_binary # strings with addresses
rabin2 -zz target_binary # all strings including wide
# Imports/Exports
rabin2 -i target_binary # imports
rabin2 -E target_binary # exports
objdump -T target_binary # dynamic symbols
# Security mitigations
checksec --file=target_binary
# RELRO, Stack Canary, NX, PIE, FORTIFY
Disassembly & Decompilation
# Ghidra headless analysis
analyzeHeadless /tmp/ghidra_project proj -import target_binary \
-postScript ExportDecompilation.java -scriptPath /scripts/
# radare2 analysis
r2 -A target_binary
> afl # list functions
> axt @sym.target_func # xrefs to function
> pdf @main # disassemble function
> VV @main # visual graph mode
> afn new_name @addr # rename function
# IDA (via MCP or IDAPython)
# Decompile function, rename variables, set types
# Cross-references: xrefs_to(addr), xrefs_from(addr)
Pattern Recognition
# Common vulnerability patterns in disassembly:
# - strcpy/sprintf without bounds → buffer overflow
# - malloc(user_controlled_size) → integer overflow
# - free() followed by use → UAF
# - system()/exec() with user data → command injection
# - Custom crypto (XOR loops, fixed keys) → weak encryption
Dynamic Analysis
Debugging
# GDB with pwndbg/GEF
gdb -q ./target
> break *main
> run
> vmmap # memory layout
> heap # heap state
> telescope $rsp 20 # stack inspection
> search-pattern "AAAA" # find pattern in memory
# Conditional breakpoints
> break *0x401234 if $rax == 0x41414141
> commands
> x/s $rdi
> continue
> end
# Anti-debug bypass
> catch syscall ptrace
> commands
> set $rax = 0
> continue
> end
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 · 206 lines · 30 tokens per session scan B 3af38589ef9c
reverse-engineering is a skill published in the GitHub repository jessefmoore/offensive-claude-code (2 stars, last pushed 3mo ago), licensed MIT. It adds 30 tokens to every session and 1,461 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…