session-logs

Search and analyze JSONL conversation logs using jq and rg.

Updated Mar 10, 2026

Search Tags:#logs #search #conversation history #data analysis #jq #session logs

Ready to run

npx skills add https://github.com/lemonlqf/openclaw-rtsp --skill session-logs-lemonlqf

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: session-logs
Source: https://github.com/lemonlqf/openclaw-rtsp/tree/main/skills/session-logs
Command: npx skills add https://github.com/lemonlqf/openclaw-rtsp --skill session-logs-lemonlqf

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jq, rg, and includes references (resource) components.

What problem does it solve?

This Skill allows you to search and analyze your past conversation logs, which are stored in JSONL files, enabling you to recall previous discussions or context.

Core Features & Use Cases

Session Log Search: Query historical conversations stored in ~/.openclaw/agents/<agentId>/sessions/.
Data Analysis: Utilize jq to filter and extract specific information like user messages, assistant responses, costs, and tool usage.
Use Case: When a user asks about a decision made in a previous, unrelated conversation, you can use this skill to find that conversation and extract the relevant details.

Quick Start

Use the session-logs skill to search all sessions for the phrase "project deadline".

Frequently Asked Questions about session-logs

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

FAQPage Schema

How do I search past conversation logs stored in JSONL format?▼

To search conversation logs in JSONL format, you can filter and extract user messages, assistant responses, and cost data from session files using jq and rg for pattern matching and structural querying.

How do I extract specific messages from session history using jq?▼

Extract specific messages from session history by applying jq filters to the JSONL files located in your agents sessions directory, targeting user messages, assistant responses, or tool usage data individually.

Do I need jq and rg installed to analyze session transcripts?▼

Yes, you need both jq and rg installed to analyze session transcripts, as jq handles JSONL data filtering and extraction while rg performs fast pattern matching within the session files.

Can I retrieve cost data and tool usage from previous chat sessions?▼

You can retrieve cost data and tool usage from previous chat sessions by querying the JSONL session transcripts with jq, allowing you to extract and review historical context and specific metadata.

What is the best way to find a decision made in an unrelated previous conversation?▼

The best way to find a past decision is to search all stored session logs using rg for keyword pattern matching, then use jq to extract the relevant conversational context from the matched JSONL files.

Where are my agent session transcripts stored for log analysis?▼

Agent session transcripts are stored as JSONL files in the ~/.openclaw/agents/<agentId>/sessions/ directory, allowing you to perform log analysis and retrieve historical conversation context locally.