setup-memory

Moves per-project Claude memory into the repo and links it back via a filesystem junction.

2|1|Updated Jun 23, 2026
One-click install
npx skills add https://github.com/Kaidanov/grekai-skills-4all --skill setup-memory-kaidanov
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: setup-memory
Source: https://github.com/Kaidanov/grekai-skills-4all/tree/main/skills/setup-memory
Command: npx skills add https://github.com/Kaidanov/grekai-skills-4all --skill setup-memory-kaidanov

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and assets (resource) components.

What problem does it solve? Claude's per-project memory normally lives outside the repo at ~/.claude/projects/<slug>/memory/, so it is never versioned, never shared with the team, and lost when switching machines. This Skill relocates that memory into the repository at memories/repo/ and links it back with a directory junction, making project knowledge committable, reviewable, and automatically loaded every session. ## Core Features & Use Cases - Memory-in-repo setup: Creates memories/repo/ with a MEMORY.md index skeleton (Feedback / Reference / Project / User sections) and seeds a frontmatter template for new memory files. - Automatic migration: If a real memory folder already exists under ~/.claude, its files are migrated into the repo first (never overwriting newer files) before being replaced with a junction. - Idempotent junction linking: Computes the project slug the same way the harness does and creates a directory junction (no admin rights required, unlike symlinks); re-runs are safe no-ops. - Use Case: A team lead clones a project on a new machine, runs the setup script once, and every team member's Claude sessions instantly load the same curated project context committed in git. ## Quick Start Ask Claude to set up memory in this repo so project knowledge is version-controlled and shared with the team.

Frequently Asked Questions about setup-memory

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

FAQPage Schema
How do I share Claude project memory with my team?

Move the memory into the repo at memories/repo/ and commit it, then link it back to ~/.claude/projects/<slug>/memory with a directory junction. The setup-memory script automates this, so anyone who clones the repo and runs it gets the same context.

How to set up version-controlled Claude memory in a repo?

Run the Setup-Memory.ps1 script from your repo root with -ProjectPath pointing at the repository. It creates memories/repo/, seeds a MEMORY.md index and template, and junctions the harness memory path to that folder.

Does creating a junction for Claude memory require admin rights?

No. The script uses a Windows directory junction rather than a symlink, and junctions do not require elevated privileges. It works on a standard user account.

What happens to my existing Claude memory folder when I run the setup?

Existing files in ~/.claude/projects/<slug>/memory are migrated into memories/repo/ first, and the script never overwrites a newer destination file. The emptied folder is then replaced with a junction pointing at the repo.

Is the memory setup script safe to run multiple times?

Yes, it is idempotent. Re-running on an already-linked repo is a no-op, and you can pass -WhatIf to preview changes or -Force to re-seed templates and re-point a junction.