Claude Code & Codex Usage Trading Cards by Rudel - Get your trading card based on your CC & codex usage

by
Rudel now turns your Claude Code & Codex sessions into a trading card with an archetype based on your pattern. Based on session shape, token usage, model mix, repo breadth, cost intensity, output signals, errors, and patterns. Free, open source, and self-hostable.

Add a comment

Replies

Best
Maker
📌

hey all!

we built rudel because we were using claude code / codex every day, but had no idea what was actually happening across sessions.

which sessions worked?
which ones got abandoned?
where were tokens going?
were we getting better, or just spending more?

we launched a month ago and had great reception.

so we tried something more fun: spotify wrapped x fifa ultimate team cards for claude code and codex.

upload your sessions, and rudel gives you your ai coder card.

some examples:

roadrunner: fast, frequent, high-output sessions
tourist: light usage, lots of starts, low commitment
company card: high intensity, high spend, meh output
maniac: broad, consistent, intense usage across repos
adhd brain (me): lots of repos, mid to low throughput across

and 4 more...

the classifier runs on derived metadata like duration, token counts, model mix, repo count, and commit signals.

free and open source.

would love feedback on the cards, the archetypes, and what else you’d want to understand about your claude code / codex usage.

cheers!

very cool product, congrats Evren!

 thanks peter!

For folks self-hosting — what's the resource floor? Single node or does it expect a small cluster? And how does upgrade work once a real team is depending on it — drop-in replace the binary, or is there a migration step?

 hey there! Not a black and white answer to this. Unless you have a huge team I'd assume a single 8gb node could do the trick (even if it goes down, since sessions are kept locally you can just re-upload). In regards to scalling, claude is great to handle clickhouse migrations with some guidance, but you can always just use the cloud version we provide (or use obsessionDB / clickhouse cloud). We never check users data or anything like that in any case.