session-logs

Search and analyze JSONL conversation logs with jq and ripgrep.

Updated Jun 18, 2026
One-click install
npx skills add https://github.com/wangqianCAI/OBI --skill session-logs-wangqiancai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: session-logs
Source: https://github.com/wangqianCAI/OBI/tree/main/skills/session-logs
Command: npx skills add https://github.com/wangqianCAI/OBI --skill session-logs-wangqiancai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jq, ripgrep.

What problem does it solve?

This skill solves the difficulty of retrieving and analyzing historical context from past conversations that are no longer present in the immediate memory buffer.

Core Features & Use Cases

  • Historical Search: Quickly find specific keywords or topics across all past session logs using ripgrep.
  • Data Analysis: Calculate total costs, message counts, and tool usage patterns across multiple sessions using jq.
  • Use Case: If a user asks about a decision made in a conversation from last week, this skill allows the agent to scan the JSONL logs to pinpoint the exact message and context.

Quick Start

Use the session-logs skill to search for the keyword project-alpha in all assistant responses from the current agent session logs.

Frequently Asked Questions about session-logs

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

FAQPage Schema
How do I search and analyze past conversation logs stored in JSONL format?

To search and analyze JSONL conversation logs, you can scan historical session files to retrieve context and calculate usage metrics. This process relies on jq for JSON data processing and ripgrep for high-speed text searching across the logs.

How do I calculate token costs and message counts from historical session logs?

Calculate token costs and message counts from session logs by applying jq to parse the JSONL files. This allows you to extract usage metrics and identify recurring patterns in agent-user communication across multiple past sessions.

Can I use ripgrep to find specific keywords across all past conversation history?

Yes, you can use ripgrep to perform historical searches across all past conversation history. It enables high-speed text searching to pinpoint specific keywords or topics within your JSONL session logs.

Do I need jq and ripgrep installed to audit past agent interactions?

Yes, you need both jq and ripgrep installed to audit past agent interactions. jq is required for JSON processing to calculate costs and counts, while ripgrep is necessary for high-speed text searching across your JSONL session files.

What is the best way to retrieve context from a conversation that is no longer in the memory buffer?

The best way to retrieve context outside the memory buffer is to search historical conversation logs stored in JSONL format. This allows you to scan past session files to pinpoint exact messages and context from previous interactions.

Can I identify recurring patterns in agent-user communication using JSONL session logs?

Yes, you can identify recurring patterns in agent-user communication by analyzing JSONL session logs. Using jq for data analysis allows you to calculate tool usage patterns and extract metrics across multiple historical sessions.