advise
Critical thinking analysis - validates alignment, challenges assumptions, identifies risks
Search past observations and context from claude-mem persistent memory
$ npx -y skills add akaszubski/autonomous-dev --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/mem-searchContext preview
What this command does when you run it.
Search past observations and context from claude-mem persistent memory
name: mem-search description: Search past observations and context from claude-mem persistent memory argument-hint: Search query (e.g., "authentication patterns" or "error handling") allowed-tools: [Bash, Read] disable-model-invocation: true user-invocable: true user_facing: true
Search past observations, context, and tool outputs captured by the [claude-mem](https://github.com/thedotmack/claude-mem) persistent memory plugin.
This command requires claude-mem to be installed and running:
1. **Install claude-mem**: See https://github.com/thedotmack/claude-mem 2. **Worker service running**: Should be on port 37777 3. **Validate**: Run `/health-check` to verify prerequisites
ARGUMENTS: {{ARGUMENTS}}
First, verify claude-mem is installed and the worker is running:
# Check if claude-mem directory exists
if [ ! -d ~/.claude-mem ]; then
echo "ERROR: claude-mem not installed"
echo "Install from: https://github.com/thedotmack/claude-mem"
exit 1
fi
# Check if worker is running on port 37777
if ! curl -s http://localhost:37777/health > /dev/null 2>&1; then
echo "WARNING: claude-mem worker may not be running"
echo "Start with: cd ~/.claude-mem && bun run worker"
fiIf the MCP server `claude-mem` is available, use its search tool:
mcp__claude-mem__search_observations(query="ARGUMENTS")
If MCP is not available, query the SQLite database directly:
sqlite3 ~/.claude-mem/data/memory.db " SELECT timestamp, content FROM observations WHERE content LIKE '%QUERY%' ORDER BY timestamp DESC LIMIT 20 "
Replace `QUERY` with the search term from ARGUMENTS.
Format and display the search results:
The claude-mem plugin captures tool observations throughout your sessions:
This command searches that history to:
# Search for authentication patterns /mem-search authentication # Find error handling approaches /mem-search "error handling" # Look for specific file mentions /mem-search config.json # Search for recent changes /mem-search "git commit"
Search returns:
Install from: https://github.com/thedotmack/claude-mem
cd ~/.claude-mem && bun run worker
---
**Part of**: claude-mem integration (GitHub #327) **Related**: `/health-check`
A harness that wraps Claude Code with enforcement, specialist agents, and alignment gates to deliver consistent, production-grade software engineering outcomes.
Repo: akaszubski/autonomous-dev
Critical thinking analysis - validates alignment, challenges assumptions, identifies risks
Comprehensive quality audit - code quality, documentation, coverage, security
Autonomous experiment loop — hypothesize, modify, benchmark, commit or revert
Create GitHub issue with automated research (--quick for fast mode)
Autonomous queue drainer — picks the top /triage cluster, applies safety gates, drains via /implement --issues, pushes, deploys.