I was playing around with LLMs, but I kept running out of tokens. A lot of them went to reading files, often ones that had nothing to do with my prompt.
Weekly usage100%
Resets in 4 days
When you're looking for something, you don't read everything. You skim the headings or the first line of a paragraph, and read closely only when you find something relevant. I wanted an agent to do the same.
I wrote two Claude Code skills for it. The first, checkpoint, writes a short description of every file in a folder. The second, skim, has the agent read those descriptions first and only open the files that matter.
I'm still working on ways to improve my workflow.