session-logs

Parse JSONL session logs to surface past messages, costs, and tool usage.

Updated Apr 5, 2026
One-click install
npx skills add https://github.com/balic-AI-ML-R-D-Resources/eliza_autonomous_agents --skill session-logs-balic-ai-ml-r-d-resources
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: session-logs
Source: https://github.com/balic-AI-ML-R-D-Resources/eliza_autonomous_agents/tree/main/packages/skills/skills/session-logs
Command: npx skills add https://github.com/balic-AI-ML-R-D-Resources/eliza_autonomous_agents --skill session-logs-balic-ai-ml-r-d-resources

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables you to retrieve and inspect historical session data stored as JSONL logs, helping you recall past conversations, tool usage, and costs across sessions.

Core Features & Use Cases

  • Retrieve complete session histories from ~/.otto/agents/<agentId>/sessions/ and parse per-session JSONL files.
  • Query for user or assistant messages, timestamps, and cost data to understand interactions and spending during conversations.
  • Use for audits, cost optimization, or context reconstitution when memory is incomplete.

Quick Start

Search all stored sessions in ~/.otto/agents/<agentId>/sessions/*.jsonl for a keyword and surface matching messages.

Frequently Asked Questions about session-logs

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

FAQPage Schema
How do I search conversation history for a specific keyword across past sessions?

You can search conversation history by querying JSONL session logs stored in the agents directory. The skill parses these files to surface matching user or assistant messages containing your target keyword across past sessions.

Can I retrieve token usage and cost data from past session logs?

Yes, you can retrieve token usage and cost data from JSONL session logs. The skill queries structured message data to extract cost information and timestamps, enabling audits and cost optimization across historical conversations.

What is the best way to restore context from older conversations when memory is incomplete?

The best way to restore context is by parsing JSONL session files to extract historical user and assistant messages. This skill surfaces past session log information, providing accurate context restoration when working memory is incomplete.

Does this tool work with JSONL files stored in the Otto agents directory?

Yes, this tool directly accesses and parses JSONL files stored in the Otto agents sessions directory. It is designed to read per-session JSONL files to retrieve complete session histories and tool interactions for review.

How do I audit tool interactions across multiple stored sessions?

You audit tool interactions by parsing JSONL session logs to review historical tool usage and message data. The skill surfaces information from past session logs, enabling thorough audits across all stored sessions.

What are the limitations when searching historical session data?

The primary limitation is that this skill relies on the availability of JSONL session files in the agents directory. If historical session logs were not stored or were deleted, the tool cannot parse or surface that missing conversation data.