# Token Saver Memory Dedup

> Helper skill that deduplicates token-saver memory records before persistence.

- Skill: `oimiragieo/token-saver-memory-dedup` (Agent Skill, multi-file: 10 files)
- Install (CLI): `npx skillmds@latest add oimiragieo/token-saver-memory-dedup`
- Raw SKILL.md: https://api.skillmd.com/api/skills/oimiragieo/token-saver-memory-dedup/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: oimiragieo (https://skillmd.com/u/oimiragieo)
- Updated: 2026-09-10
- Page: https://skillmd.com/skills/oimiragieo/token-saver-memory-dedup

---


# Token Saver Memory Dedup

Deduplicates memory records against existing memory files to prevent duplicate entries.

## Purpose

This skill provides the `deduplicateAgainstMemory` function that filters out memory records that already exist in the memory system:

- Compares incoming records against `patterns.json` and `gotchas.json`
- Case-insensitive matching for deduplication
- Returns statistics about total, kept, and filtered records
- Handles corrupt or missing memory files gracefully

## Usage

```javascript
const { deduplicateAgainstMemory } = require('./scripts/main.cjs');

const records = {
  patterns: [{ text: 'Use canonical transitions', timestamp: '2026-01-01', source: 'test' }],
  gotchas: [{ text: 'Avoid shell: true for spawn', timestamp: '2026-01-01', source: 'test' }],
  issues: [],
  decisions: [],
};

const { dedupedRecords, stats } = deduplicateAgainstMemory(records, '/path/to/memory');
```

## When to Use

- Before persisting memory records to avoid duplicates
- As part of the token-saver-context-compression workflow
- When syncing memory records between sessions

## Implementation

Re-exports the `deduplicateAgainstMemory` function from `token-saver-context-compression` for module resolution and testing purposes.