Why Claude Code Re-Introduces Itself to Your Repo

Ever wonder why Claude Code re-scans your repository every session, even when nothing's changed? This episode unpacks the distinction between instruction memory and structure memory, and why the harness optimizes for freshness over recall. We explore the third-party tools that already solve this problem — Aider's repo maps, repomix, context7, and MCP servers — and the system-prompt hacks that can wire them in. Plus, we discuss the real frontier: judgment memory, the institutional knowledge no tool has captured yet. Episode #808052 — open it directly at myweirdprompts.com/808052