JJ Englert(@JJEnglert):Opus 5.5 is crushing the game right now. Here's a prompt that you can copy and paste into Claude to audit your tool calls and improve efficiency even more. ---- Look through my Claude Code chat history for this repo in ~/.claude/projects/. 1. Find the files and folders agents visit most often. 2. For each one, count how many tool calls it usually took to get there, and roughly how many tokens that used. 3. Flag the paths where the agent searched, opened the wrong files, or backtracked before finding the right spot. 4. Rank the 5 most wasteful paths by total tokens burned. 5. Suggest the smallest CLAUDE.md edits that would send an agent straight there. Pointers, not paragraphs. Don't change any files yet. Show me the report first. --- Thank me later 😉

2026.09.23 20:04

Opus 5.5 is crushing the game right now. Here's a prompt that you can copy and paste into Claude to audit your tool calls and improve efficiency even more. ---- Look through my Claude Code chat history for this repo in ~/.claude/projects/. 1. Find the files and folders agents visit most often. 2. For each one, count how many tool calls it usually took to get there, and roughly how many tokens that used. 3. Flag the paths where the agent searched, opened the wrong files, or backtracked before finding the right spot. 4. Rank the 5 most wasteful paths by total tokens burned. 5. Suggest the smallest CLAUDE.md edits that would send an agent straight there. Pointers, not paragraphs. Don't change any files yet. Show me the report first. --- Thank me later 😉

显示更多

Claude@claudeai

2026.09.22 16:31

Introducing Claude Opus 5.5, the first model in our new Claude 5.5 family. It performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.