Claude Code users can identify high-context tools with local script
A developer has released a script called jCodeMunch that analyzes local Claude Code session logs. The script helps users identify which tools are consuming the most context window space during their coding sessions. Claude Code includes the full conversation history with each request, and tool results remain in the session until cleared. The script works by parsing local JSONL session files to count tokens returned by each tool. This allows users to optimize their workflow without sharing data externally.
This is an AI-generated summary. ShortSingh links to the original source for the complete article.
Discussion (0)
Log in to join the discussion and vote.
Log in