Why Claude.md Keeps Growing: The Cost of Deleting vs. Adding Instructions

量子位 · wechat · 2026-08-15

Core Finding

Research reveals that instruction files like Claude.md often balloon to over 3x their initial size—a phenomenon termed "catastrophic remembering." A survey of 2,000 GitHub repos shows an average instruction growth of 226%.

Root Cause

Solution

Adding effective annotations (recording the trigger, logic, and validation result) is key. Experiments show that well-annotated prompts reduced excess instruction size from 211.3% to 1.4%, cutting 99.3% of redundancy without sacrificing accuracy.

Industry Insight

The article calls for AI tool providers to upgrade infrastructure, establishing an "instruction + evidence" update mechanism so tools can actively verify and "forget," rather than just storing final rules.

Original post →

More from coding & agent

coding & agent channel →