Anthropic engineer on Claude Code effort levels: low for staying in the loop, max for security audits

trq212 · x · 2026-09-26

Anthropic engineer trq212 published a deep dive on effort levels in Claude Code: the newest Claude models respond to effort without breaking the prompt cache, but users are unsure which level to pick. His practice: effort low is used a lot when staying in the loop; effort max is basically only for fully hands-off runs or hunting security vulnerabilities. The article digs into evals to explain why effort exists and how models behave at each level.

Related event: Anthropic Explains Claude Code Effort Setting(4 posts)→

Original post →

More from coding & agent

coding & agent channel →