session-logs

Search and analyze OpenClaw session JSONL files for historical messages.

Updated Feb 16, 2026
One-click install
npx skills add https://github.com/RobbyMo81/assistantrobby --skill session-logs-robbymo81
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: session-logs
Source: https://github.com/RobbyMo81/assistantrobby/tree/main/skills/session-logs
Command: npx skills add https://github.com/RobbyMo81/assistantrobby --skill session-logs-robbymo81

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides a straightforward way to locate and inspect historical conversation data that is not present in memory or the current context, enabling accurate follow-up, clarification, and auditing of past agent interactions.

Core Features & Use Cases

  • Indexed session browsing: Use the sessions.json index to locate session files and list sessions by date and size.
  • Role‑based content extraction: Extract and filter user, assistant, or tool messages from JSONL transcripts for review or summarization.
  • Cost and usage analysis: Compute per-session or daily cost totals from message usage metadata to monitor spend.
  • Use Case: Find what was discussed in a parent conversation to resolve user follow-up questions or recover context for a long-running task.

Quick Start

Search the session logs for the phrase keyword and return matching user and assistant messages with their timestamps.

Frequently Asked Questions about session-logs

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

FAQPage Schema
How do I search OpenClaw conversation history for a specific keyword?

To search OpenClaw conversation history, you can filter JSONL session logs by message content using ripgrep. This returns matching user and assistant messages along with their timestamps for context recovery.

How do I extract assistant responses from JSONL session logs?

You can extract assistant responses from JSONL session logs by parsing message entries and filtering on the message.role field. This isolates assistant outputs from user and tool messages for targeted review or summarization.

Can I compute per-session cost totals from OpenClaw session metadata?

Yes, you can compute per-session cost totals from OpenClaw session metadata. The tool parses usage metadata within JSONL entries to calculate and report daily or per-session spend for monitoring purposes.

Do I need jq and ripgrep installed to search JSONL session files?

Yes, you need jq and ripgrep installed to efficiently query JSONL session files. The tool assumes availability of jq for structured JSON parsing and ripgrep for fast text searching across the session store.

What is the best way to locate prior OpenClaw session files by date?

The best way to locate prior OpenClaw session files by date is using the sessions.json index. This index allows you to browse and list historical sessions chronologically along with their file sizes.

Why does recovering context from long-running agent sessions require log analysis?

Recovering context requires log analysis because historical conversation data is not present in active memory. Parsing JSONL transcripts retrieves prior user messages and assistant responses needed to resolve follow-up questions.