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/transilienceai/communitytools/reverse-engineeringnpx skills add transilienceai/communitytools --skill reverse-engineeringgit clone --depth 1 https://github.com/transilienceai/communitytoolsWhat 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 | $0.00032 | $0.00356 |
| Opus 5 | $0.00016 | $0.00178 |
| Sonnet 5 | $0.00006 | $0.00071 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
reverse-engineering 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.
What it actually says
Reverse Engineering
Scope
Reverse engineering compiled binaries (ELF, PE, Mach-O) and bytecode artifacts to recover algorithms, validate inputs, or build static solvers. Focused on the recurring CTF / malware-analysis pattern of a host binary that loads a "program" file under a custom ISA — recognising the dispatcher loop, mapping opcodes to Python lambdas, and inverting the transformation chain in pure Python without executing the host. Also covers callfuscation (control-flow chunking), MBA (mixed boolean-arithmetic) operator obfuscation, encrypted-handler tricks, and three-layer deobfuscation pipelines.
When to use
- A binary plus a "program data" file are delivered together and the binary appears to be an interpreter (themed opcode names, dispatcher switch / jump table).
- Disassembly reveals a
while(true){ op = mem[pc++]; switch(op){...}; }style loop or jump-table indexed by opcode. - The binary is heavily obfuscated (callfuscation, MBA wrappers, encrypted handlers in
.datadecrypted to RWX at startup). - You need to recover an algorithm or check function from native code without dynamic execution (anti-debug, wrong arch, no TTY).
- Static-first reverse engineering is preferred (faster, more reliable than emulator chains).
References
- reference/custom-vm-bytecode.md — recognising and inverting custom stack/register/tape VMs; callfuscation linearization; MBA operator identification; encrypted-handler decryption.
What ships with it
25 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- reference/custom-vm-bytecode.md 6.7 KB
- reference/INDEX.md 4.4 KB
- reference/reverse-engineering-principles.md 4.7 KB
- reference/scenarios/anti-debug/int3-detection-bypass.md 4.4 KB
- reference/scenarios/anti-debug/isdebuggerpresent-bypass.md 4.6 KB
- reference/scenarios/anti-debug/ptrace-bypass.md 4.5 KB
- reference/scenarios/anti-debug/timing-checks-bypass.md 4.4 KB
- reference/scenarios/custom-vm/bytecode-disassembly.md 6.7 KB
- reference/scenarios/dynamic-analysis/frida-hooking.md 4.7 KB
- reference/scenarios/dynamic-analysis/gdb-scripting.md 4.8 KB
- reference/scenarios/dynamic-analysis/ltrace-strace.md 4.1 KB
- reference/scenarios/firmware/esp32-xtensa-flash-dump.md 6.1 KB
- reference/scenarios/kernel/kernel-rootkit-module.md 6.4 KB
- reference/scenarios/obfuscation/callfuscation.md 5.0 KB
- reference/scenarios/obfuscation/d-fiber-callfuscation.md 14 KB
- reference/scenarios/obfuscation/hash-dispatcher-chain.md 7.5 KB
- reference/scenarios/obfuscation/mba-deobfuscation.md 5.1 KB
- reference/scenarios/obfuscation/packed-binaries.md 4.7 KB
- reference/scenarios/obfuscation/python-bytecode-payload.md 4.9 KB
- reference/scenarios/obfuscation/string-obfuscation.md 5.4 KB
- reference/scenarios/static-analysis/disassembly-recipe.md 5.1 KB
- reference/scenarios/static-analysis/elf-analysis.md 4.6 KB
- reference/scenarios/static-analysis/pe-analysis.md 4.6 KB
- reference/scenarios/static-analysis/string-extraction.md 4.4 KB
- reference/scenarios/static-analysis/unity-il2cpp-recipe.md 11 KB
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.
- 2d ago First seen · 23 lines · 32 tokens per session scan A b47e61c9830b
reverse-engineering is a skill published in the GitHub repository transilienceai/communitytools (498 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 356 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pentester-playwright
Phases 1b/3/4 authorized browser automation — SPA recon, multi-role auth, route/API catalog, PoC screenshots, Evidence landing (scoped proxy). Skill-gate read for web phases. Use when Phase 1b/3/4 web work, JS-rendered SPA, real browser needed, HAR/network capture, or Playwright PoC evidence.
osint-recon
Phase 1 conditional OSINT depth — four-dimension model (server→site→domain→people; people is conditional). Skill-gate companion to pentester-enum-services / pentester-recon. Use for passive OSINT depth, full recon dimensions, author tracking, not as Phase 0/Schema replacement.
pentester-exploit
Phase 4 exploitation — PoC construction, exploit-db/msf search, safe verification. Required Skill-gate read at Phase 4. Use when starting Phase 4, exploitation, exploit, PoC, exploit-db, msf, Metasploit, or payload delivery.
pentester-recon
Phase 1 intelligence recon methodology — passive+active recon, stack fingerprint, attack-surface map. Required Skill-gate read at Phase 1 (with pentester-enum-services). Use when starting Phase 1, intelligence gathering, recon, reconnaissance, OSINT prep, target profiling, or attack surface mapping.
pentester-toolkit
Provision the pinned pentest toolset via DotSlash for the current scanenv (host-kali or kali-target-${ID}). Adapter, not a tool wrapper.
pentester-waf-bypass
Phase 4 conditional — WAF/filter bypass for authorized CTF/range/pentest when payloads are blocked. Use at Phase 4 if blocked, or when user mentions WAF bypass, filter evasion, SQL/XSS/command-injection bypass, or security filter analysis.