Reverse Engineering Reveals True Reduction in Claude Code System Prompts
PawelHuryn · x · 2026-07-22
Addressing rumors of an 80% cut to Claude Code's system prompt, the author captured the real prompts for all 6 models using a fake ANTHROPICBASEURL. The analysis reveals the actual reduction is closer to 70%: the 80% figure only applies when memory is disabled. The memory rules weren't deleted but are simply not loaded when memory is off. The repository includes the full system prompts, diffs between them, and a one-command trick to capture any model's real prompt.
Related event: Reverse Engineering Shows Claude Code Prompts Reduced by 70%(2 posts)→
More from coding & agent
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11
- Codex tip: use Sol with Astra and Luna sub-agents to save usage — pvncher · 2026-09-11
- agents-best-practices: a provider-neutral Agent Skill for designing and auditing agentic harnesses — tom_doerr · 2026-09-11
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- First-ever Three.js Conference lands in Paris, with a panel on AI-shortened design workflows — OdinLovis · 2026-09-11
- Agile co-author Ron Jeffries publishes 'Resist AI', urging developers to push back — mborch · 2026-09-11