Hacker News
points by bprathamesh2003 19 hours ago | 0 comments
I think claude code is bloated as a harness now. It was clean when it launched but now anthropic is bombarding it with features.
[–] edstarch 18 hours ago
10k tokens of bullshit on "artifacts"

It can be slimmed down pretty aggressively: turn off a few features (claude.ai connector sync, artifacts), work with Claude to disable / defer as many skills and tools you don't need (e.g. SendFeedback), use `--system-prompt ""`. Would be better to just skip all that to begin with but that's the cost of a subsidized fixed price plan.

[–] odo1242 7 hours ago
They do seem to have successfully moved all of the stuff relating to artifacts out to skills with the latest release.
[–] bprathamesh2003 18 hours ago
Have you noticed any quality drop with `--system-prompt ""`? A lot of the tool-use guidance lives in there, so I'd worry about swapping bloat for worse behavior. A lean core with everything else opt-in would be the ideal.
[–] edstarch 15 hours ago
I have not. Obviously YMMV, but tools have ~8k tokens of descriptions of their own, including (imo too much) behavioural guidance. The tool descriptions are retained with `--system-prompt ""`, I'm sure you can get Claude to output what's in there exactly as it changes quite a lot between versions.