Read my entire setup before responding. Check my CLAUDE.md (global and project-level), every skill in my skills folder, every file in my context folder, and any other instruction files you can find.

## Part 1: Instruction Audit
For each rule, instruction, and preference you find:
1. Is this something you already do by default without being told?
2. Does this contradict or conflict with another rule somewhere else in my setup?
3. Does this repeat something that's already covered by a different rule or file?
4. Does this read like it was added to fix one specific bad output rather than improve outputs overall?
5. Is this so vague that you'd interpret it differently every time? (ex: "be more natural" or "use a good tone")

Then give me:
- A list of everything you'd cut, with a one-line reason for each
- A list of any conflicts you found between files
- A cleaned-up version of my CLAUDE.md with the dead weight removed

## Part 2: Memory Pruning
Memory pruning has its own command — run `/memory-cleanup` separately. It accumulates faster than instructions and benefits from a dedicated cadence.

While doing the instruction audit above, flag any CLAUDE.md rule that's also covered by an auto-memory entry — those duplicates get resolved on the next `/memory-cleanup` pass.

## Part 3: Efficiency Check
Based on everything you've read, identify:
- Any instructions that slow you down without adding value (e.g., excessive confirmation steps for low-risk actions)
- Any patterns where the setup causes you to spawn agents or do research for things you could answer directly
- Any missing rules that would prevent repeated mistakes you've seen in the memory/feedback entries