From memstack
Saves and restores project state between Claude Code sessions. Captures session accomplishments, pending work, and next steps, then stores context in SQLite and markdown handoff files for seamless continuation.
How this skill is triggered — by the user, by Claude, or both
Slash command
/memstack:projectThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
*Save and restore project state between CC sessions for seamless handoffs.*
Save and restore project state between CC sessions for seamless handoffs.
When this skill activates, output:
💾 Project — Saving project state...
Then execute the protocol below.
python "$MEMSTACK_PATH/db/memstack-db.py" set-context '{"project":"<name>","status":"active","current_branch":"<branch>","last_session_date":"<YYYY-MM-DD>","known_issues":"<issues>","backlog":"<next tasks>"}'
memory/projects/{project}-{date}.mdpython "$MEMSTACK_PATH/db/memstack-db.py" get-context <project>
python "$MEMSTACK_PATH/db/memstack-db.py" get-sessions <project> --limit 3
python "$MEMSTACK_PATH/db/memstack-db.py" get-plan <project>
memory/projects/ for markdown handoffsUser: "context is running low — save project"
💾 Project — Saving project state...
Saved: memory/projects/adminstack-2026-02-18.md
--- PASTE INTO NEXT CC SESSION ---
Working directory: /path/to/your-project
Read $MEMSTACK_PATH/MEMSTACK.md
Resume AdminStack. Last session completed:
- Built CC Monitor page with auto-refresh
- Fixed API key validation
Next steps:
1. Build cc-reporter.js script
2. Add WebSocket updates
--- END HANDOFF ---
npx claudepluginhub cwinvestments/memstack --plugin memstackMaintains a living STATE.md document tracking current project context, active tasks, blockers, and next steps. Auto-loads at session start or on explicit commands like 'update state' or 'where was I'.
Persists project memory across Claude Code sessions. Auto-loads context on startup, tracks git activity, and saves session state via deterministic Node.js scripts.