8000 [Question] Regarding the number of tokens of CLAUDE.md and it's apendices. · Issue #64 · NomenAK/SuperClaude · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
[Question] Regarding the number of tokens of CLAUDE.md and it's apendices. #64
Open
@filipejunqueira

Description

@filipejunqueira

Question Type

Other

Your Question

How does CC loads the config files? If it loads everything than we have a 70k issue!

Context

I've cat the entirety of Claude.md with the other .mds that it reference + all the commands and all that yields according to chatgpt token counter about 70k tokens. I'm not sure how CC loads the configuration at .claude but if loads all files, than we are getting a large portion of the context eaten just by config files, which in turn defeats the purpose of SuperClaude. I'd love to be wrong but the fact that I have Context left until auto-compact so often makes me wonder how CC is loading these files and weather SuperClaude needs to be reduced significantly.

Current Configuration

No response

What Have You Tried?

No response

Checklist

  • I have read the README.md
  • I have searched existing issues and discussions
  • This is not a bug report (use Bug Report template instead)

Metadata

Metadata

Assignees

No one assigned

    Labels

    questionFurther information is requested

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions

      0