dream-memory-consolidation

Consolidate Claude Code memory files by aligning signals from transcripts and daily logs.

Updated Apr 17, 2026
One-click install
npx skills add https://github.com/UsernameTron/Pete-Gets-Shit-Done --skill dream-memory-consolidation
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dream-memory-consolidation
Source: https://github.com/UsernameTron/Pete-Gets-Shit-Done/tree/main/.claude/skills
Command: npx skills add https://github.com/UsernameTron/Pete-Gets-Shit-Done --skill dream-memory-consolidation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Consolidates Claude Code memories by aligning local memory files with recent signals from transcripts and daily logs, deduplicating entries, resolving contradictions, converting relative dates to absolute, and pruning the MEMORY.md index to stay under 200 lines / 25KB.

Core Features & Use Cases

  • Multi-source signal fusion: aggregates signals from logs, transcripts, and memory entries to keep context accurate.
  • Contradiction detection & pruning: identifies inconsistencies and retires stale or duplicate memories to maintain a lean index.
  • Scope routing & governance: supports project, user, or both scopes and enforces memory lifecycle rules (200 lines / 25KB limit).

Quick Start

Run the dream-memory-consolidation to orient Claude memory, gather signals, and prune MEMORY.md for the chosen scope.

Frequently Asked Questions about dream-memory-consolidation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I consolidate Claude Code memories from transcripts and logs?

Memory consolidation for Claude Code works by aggregating signals from logs and transcripts, resolving contradictions, and converting relative dates to absolute to keep your memory index accurate.

Why does my Claude Code MEMORY.md file keep growing past the size limit?

Your MEMORY.md file exceeds size limits because stale or duplicate entries accumulate over time; memory consolidation prunes the index to stay under strict 200 lines or 25KB constraints.

Can I automate memory consolidation for both project and user scopes in Claude Code?

Yes, you can automate memory consolidation across project, user, or both scopes simultaneously, applying governance rules to route signals and maintain the memory lifecycle correctly.

What is the best way to resolve contradictions in Claude Code memory files?

The best way to resolve contradictions in Claude Code memory files is through multi-source signal fusion, which identifies inconsistencies and retires stale or duplicate memories to maintain a lean index.

Does Claude Code memory consolidation require reading full JSONL transcript files?

No, Claude Code memory consolidation disallows full JSONL reads, instead gathering recent signals from transcripts and daily logs to safely fuse and update memory entries without reading entire files.