Claude Code’s prompt cut is closer to 70%, and only on frontier models
PawelHuryn · x · 2026-07-22
The author says the widely cited "80% prompt cut" for Claude Code is overstated, and the real reduction is closer to 70% for frontier models.
What changed
- For Opus, the prompt shrinks from 2,686 words to 514 with memory off, but the memory rules were not deleted.
- When memory is included, the real drop is from 2,686 words to 830.
- The stripped prompt only applies to frontier models like Opus 4.8 and Fable 5; Sonnet 5 and Haiku 4.5 still keep the older, longer instruction set.
Why Anthropic did it
Anthropic’s explanation is simple: smarter models need fewer instructions.
The takeaway is that if your CLAUDE.md keeps growing, you may be writing for a weaker model than the one you are actually using.
Related event: Reverse Engineering Shows Claude Code Prompts Reduced by 70%(2 posts)→
More from coding & agent
- LM Studio’s Bionic launches as a local-first agent for docs, coding and voice — nicolascraske · 2026-07-25
- 'Clean Code' Author Rebuts: True Engineering Beats Vibecoding — burny_tech · 2026-07-25
- AI Security Agent Achieves RCE on GitLab Default Configuration via Dependency Chain — andreamichi · 2026-07-25
- MongoDB guide maps the production stack that makes AI agents work — TheTuringPost · 2026-07-25
- A Type Proposal Would Make Inline React Arrays Fail at Build Time — aidenybai · 2026-07-25
- Long-running agents need trustworthy verification, not just more loops — hugobowne · 2026-07-25