session-memory

Persist cross-session learnings to .claude/memory with decisions.md, patterns.md, and context.json.

39|46|Updated May 29, 2026
One-click install
npx skills add https://github.com/maxwell2732/claudecode-research-harness-workflow --skill session-memory-maxwell2732
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: session-memory
Source: https://github.com/maxwell2732/claudecode-research-harness-workflow/tree/main/skills/session-memory
Command: npx skills add https://github.com/maxwell2732/claudecode-research-harness-workflow --skill session-memory-maxwell2732

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This sub-skill manages cross-session handoff, durable learning, and memory persistence by recording and referencing learnings, decisions, and patterns to sustain continuity across Claude Code workflows.

Core Features & Use Cases

  • Persists and organizes session history, decisions, and patterns under .claude/memory to enable seamless handoffs between sessions.
  • Provides a clear separation between shared SSOT memory and local session context to improve auditability and reproducibility.
  • Supports long-running research projects, iterative analysis, and knowledge continuity across multiple sessions.

Quick Start

Load the cross-session memory module and begin recording learnings to .claude/memory for future reference.

Frequently Asked Questions about session-memory

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

FAQPage Schema
How do I keep learning across Claude Code sessions without losing context?

To keep learning across Claude Code sessions, persist session history, decisions, and patterns to .claude/memory. This maintains continuity and traceability for long-running research and iterative analysis workflows.

What's the best way to manage project handoffs and maintain memory persistence?

Project handoffs and memory persistence are managed by recording learnings, decisions, and patterns to a structured .claude/memory directory, enabling seamless session transitions and durable knowledge continuity.

How does cross-session memory separation improve auditability and reproducibility?

Cross-session memory separation improves auditability by isolating shared SSOT memory from local session context. This clear data separation ensures traceability and reproducibility across iterative analysis workflows.

Can I use a structured memory structure for long-running research projects?

Yes, you can use a structured memory system with decisions.md, patterns.md, and context.json for long-running research projects. It organizes cross-session learnings to sustain knowledge continuity across multiple sessions.

Do I need any external dependencies to enable durable cross-session learning?

No external dependencies are needed to enable durable cross-session learning. The system implements local .claude/memory storage with markdown and JSON files to independently record session history and patterns.