Don't. Claude is worse for everything but coding, and even then it's mostly better for coding in greenfield/small projects, and it makes a mess of large projects. The only thing really good about Claude was the plan economics, and now I'm not so sure about it.
It only makes a mess of large projects if your CLAUDE.md and docs/ are out of date.
It has a very specific style and if your project isn't in that style, it starts to enforce it -> "making a mess".
Nah bro. I have a Claude Code hall of shame, where Sonnet gets derailed by the most trivial shit, and instead of finishing actual research code that's been clearly outlined for it (like, file by file level instructions), it creates a broken toy implementation with fake/simulated output ("XXX isn't working, the user wants me to YYY, let me just try a simpler approach...") and it'll lie about it in the final report, so if you aren't watching the log, sucks to be you.
I have an extensive array of tripwires, provenance chain verifications and variance checks in my code, and I have to treat Claude as adversarial when I let it touch my research. Not a great sign.