Claude Memory Curator

Goal

Audit Claude Code durable context as user-owned agent state: expose stale, unsafe, duplicated, over-broad, conflicting, misplaced, or unenforceable entries; propose better destinations; and apply cleanup only after a report, backup, and explicit approval.

Keep the subject scoped to Claude Code surfaces: CLAUDE.md, CLAUDE.local.md, .claude/rules/, user-level Claude rules, settings, hooks, managed policy evidence, and auto memory files. Do not treat this as a Codex, Cursor, Claude app, or Anthropic API Memory Stores curator.

When to use

• The user asks to review, audit, clean up, prune, rewrite, or remove Claude Code memory or persistent Claude instructions.
• The user mentions CLAUDE.md, CLAUDE.local.md, .claude/rules, ~/.claude/rules, /memory, auto memory, ~/.claude/projects/<project>/memory/, autoMemoryEnabled, autoMemoryDirectory, or claudeMdExcludes.
• The user wants to decide whether a Claude context entry belongs in CLAUDE.md, CLAUDE.local.md, a Claude rule, auto memory, settings, hooks, AGENTS.md, repo docs, a skill, managed policy, or deletion.
• The user reports stale Claude instructions, memory pollution, conflicting Claude rules, sensitive memory contents, or Claude repeatedly using old guidance.

When not to use