memory
Scannednpx machina-cli add skill memvid/claude-brain/memory --openclawClaude Mind
You have access to a persistent memory system powered by Claude Mind. All your observations, discoveries, and learnings are stored in a single .claude/mind.mv2 file.
How to Execute Memory Commands
Use the bundled SDK scripts via Node.js (NOT the CLI). The scripts are at ${CLAUDE_PLUGIN_ROOT}/dist/scripts/.
Search Memories
node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/find.js" "<query>" [limit]
Examples:
node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/find.js" "authentication" 5node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/find.js" "database schema" 10
Ask Questions
node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/ask.js" "<question>"
Examples:
node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/ask.js" "Why did we choose React?"node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/ask.js" "What was the CORS solution?"
View Statistics
node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/stats.js"
View Recent Memories
node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/timeline.js" [count]
Memory Types
Memories are automatically classified into these types:
- discovery - New information discovered
- decision - Important decisions made
- problem - Problems or errors encountered
- solution - Solutions implemented
- pattern - Patterns recognized in code/data
- warning - Warnings or concerns noted
- success - Successful outcomes
- refactor - Code refactoring done
- bugfix - Bugs fixed
- feature - Features added
File Location
Your memory is stored at: .claude/mind.mv2
This file is:
- Portable - Copy it anywhere, share with teammates
- Git-friendly - Commit to version control
- Self-contained - Everything in ONE file
- Searchable - Instant semantic search
Usage Tips
- Start of session: Recent memories are automatically injected as context
- During coding: Observations are captured automatically from tool use
- Searching: Use natural language queries to find relevant past context
- Sharing: Send the
.mind.mv2file to teammates for instant onboarding
Source
git clone https://github.com/memvid/claude-brain/blob/main/skills/memory/SKILL.mdView on GitHub Overview
Claude Mind stores all observations and learnings in a single .claude/mind.mv2 file. It exposes Node.js scripts (not the CLI) under ${CLAUDE_PLUGIN_ROOT}/dist/scripts to search, ask questions, view stats, and view timelines. Memories are automatically categorized into types like discovery, decision, problem, solution, pattern, warning, success, refactor, bugfix, and feature, and the file is portable and git-friendly.
How This Skill Works
The memory data lives in a portable mind.mv2 file. Use Node.js scripts located at ${CLAUDE_PLUGIN_ROOT}/dist/scripts to operate: find.js for searching, ask.js for questions, stats.js for statistics, and timeline.js for recent memories. The file is self-contained and can be shared with teammates for quick onboarding.
When to Use It
- When you need to recall past observations or learnings
- During debugging or feature work to retrieve prior decisions
- When diagnosing a problem and seeking related memories
- When reviewing past solutions and patterns for reuse
- When onboarding teammates and sharing context via the mind.mv2 file
Quick Start
- Step 1: Ensure Node.js is installed and CLAUDE_PLUGIN_ROOT is set
- Step 2: Run a search with node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/find.js" "your query" [limit]
- Step 3: Use ask.js, stats.js, or timeline.js as needed and keep .claude/mind.mv2 updated
Best Practices
- Query memories with natural language for relevant results
- Tag entries with memory types (discovery, decision, problem, solution, etc.)
- Keep the mind.mv2 file up to date and under version control
- Share the .mind.mv2 file to onboard teammates quickly
- Periodically prune or annotate memories to maintain relevance
Example Use Cases
- Find past authentication notes to understand a security decision
- Retrieve database schema discussions and changes
- Ask why a React choice was made to justify UI decisions
- Review recent CORS solution used in the project
- Check timeline of last feature implementation to aid planning
