Memory Defragmenter

Clean, merge, and optimize memory files to keep them lean and effective.

Purpose

Memory files grow over time and become:

• - Bloated with duplicates
• Stale with outdated info
• Scattered across tiers
• Inconsistent in format

This skill defragments them.

When to Run

Defragmentation Workflow

Step 1: Analyze Memory State

CODEBLOCK0

Reports:

• - Files analyzed and sizes
• Duplicate detection
• Stale entry detection (30+ days old)
• Tier distribution
• Formatting consistency

Step 2: Generate Defragmentation Plan

CODEBLOCK1

Creates defragment-plan.md with:

• - Entries to merge
• Entries to archive
• Entries to delete
• Entries to promote/demote

Step 3: Review Plan

Read the plan and approve/modify before execution.

Step 4: Execute Defragmentation

CODEBLOCK2

Backs up original files first, then:

• - Merges duplicate entries
• Archives stale content to INLINECODE1
• Promotes hot entries to HOT tier
• Demotes cold entries to archive
• Normalizes formatting

Step 5: Verify

CODEBLOCK3

Checks:

• - All files readable
• No broken links
• Consistent formatting
• Tier limits respected

Memory Tiers Reference

Safety Rules

1. 1. Always backup before executing
2. Review plan before applying
3. Never delete - only archive
4. Keep originals for 24h after
5. Verify after every defragment

Files

• - scripts/analyze_memory.py — Analyze memory state
• INLINECODE8 — Plan and execute cleanup
• INLINECODE9 — Verify integrity
• INLINECODE10 — Defragmentation rules and patterns