"We removed over 80% of Claude Code's system prompt for Opus 5 and Fable 5"

Anthropic removed over 80% of the Claude Code system prompt for its newest models Opus 5 and Fable 5, sharing lessons learned about writing system prompts, skills, and Claude.MDs for them. A user reported that Opus 5 is performing significantly better, particularly for biology tasks, after previously relying on Claude 4.6 and other models.

We removed ~80% of the Claude Code system prompt for our newest models, this is what we've learned about writing system prompts, skills and Claude.MDs for them. - Appreciate it Opus 5 is performing a lot better Was stuck relying on 4.6 + other models for biology stuff until now Join the conversation