Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Searches and analyzes conversation history stored in OpenClaw session JSONL files using jq and ripgrep. Useful when a user references prior chats or needs context from older conversations not held in memory files.
Querying raw JSONL with jq gives precise, scriptable access to full conversation history without loading entire sessions into memory.
When to use it
- Find what was discussed in a session from a specific date
- Search all past sessions for a keyword or phrase
- Calculate total API cost for a session or day
- Count messages and token usage across a conversation
- Identify which tools were used most in a session
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: what did we decide about the database schema last week?
- 1Locate the agent ID from the system prompt Runtime line
- 2List sessions from the relevant date range using the date-sorting loop
- 3Search assistant messages across those sessions for 'schema' using rg
- 4Extract matching text blocks with jq select filters
- 5Return the relevant excerpts to the user
Relevant assistant message excerpts referencing the database schema decision