Use Tokenless for large files and noisy tool outputs before they enter context. Must be used when commands, Read output, diffs, logs, or search results are large.
$npx -y skills add maxforai/tokenless --skill context-compressionInstalls into the current project.
Run `npx skills use "https://github.com/maxforai/tokenless" --skill "maxforai/tokenless/context-compression"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/maxforai/tokenless" that are relevant to the current task. Run `npx skills add "https://github.com/maxforai/tokenless"` and select the relevant skills, then follow their instructions.