Analyze the current Claude Code session for token efficiency:
Check These
- Context loaded: What CLAUDE.md, rules, and skills are currently loaded?
- MCP servers: How many tool definitions are in context?
- Conversation length: How many turns deep are we?
- File reads: Have we read the same file multiple times?
Suggest
- Whether to
/compactthe conversation - Whether to
/clearand start fresh - Which MCP servers to disable if unused
- Whether CLAUDE.md is too large
- Whether rules files should use path-scoping
Output
Session Health Report
─────────────────────
Context usage: [estimate]
Conversation turns: [count]
Suggested action: [compact / clear / continue]
Optimization tips: [specific suggestions]