I might be missing something but... How exactly is this better than telling Claude for example to "install and set up a full RE environment including Ghidra" on my local system and get to work? Like what does this do that my current RE methodology doesn't?
I don't have reverse engineering experience, though I have all the prereqs to learn it. Anecdotally a few days ago I told my slow local Qwen3.8 in Pi harness to use Ghidra CLI to decompile a certain executable and it got entirely lost. Today I was linked to this, have it chugging along now, and it's making some sort of progress towards unpacking this thing. I don't know if it will nail it this run but it's a real improvement; I definitely have some useful info I could bring to another prompt or for myself if I cared to try manually.
But I just found an even easier way I should have thought of first - someone already dropped a reimplementation a couple weeks ago.
Everybody has their own set of skills and specific scripts and tools to do this stuff. You might use Ghidra as the the kernel of those workflows, but you still want something more than just Claude freestyling, at least for now.
(Who knows if this'll be true 6 months from now.)
I don't know either. My only guess is that this has some helpful context for less powerful models, maybe.
We're kinda far into this LLM thing, maybe it's time to start selling harnesses by leading with how some examples were solved faster with this and how it saved tokens, or similar?
Why not just, like, ask Claude about it?
"Hey Claude I want to create a fanmade Game Boy game, give me recommendation of tools, libraries and workflows for it" and boom.
You can use AI to learn stuff, instead of just using it as a Pokemon.
Because it's already been done for you? Sure, you can spend your own tokens on it, but it's probably cheaper and more time-effective to use something that already exists and does the job.
I don't think it is better than just doing it yourself in Claude Code (in fact worse) but some people like cute UI for everything I guess.
We're using vanilla Claude Code for ArtCraft apps [1], but we are especially careful not to touch Ghidra. We don't want decompilations or reverse engineering to spoil the work we're doing and expose us to copyright infringement.
Probably it is not better. I think this is aimed at people who do not have a “current RE methodology”, do not know enough to specify things like Ghidra, etc., but who do have a desire to feel like they reverse-engineered and can reliably predict that a conversation with a chatbot will make them feel that way.