ce-session-inventory

Discover session files across Claude Code, Codex, and Cursor and emit JSONL metadata.

2|Updated Apr 30, 2026
One-click install
npx skills add https://github.com/thisisryanswift/zellij-agent-tools --skill ce-session-inventory
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ce-session-inventory
Source: https://github.com/thisisryanswift/zellij-agent-tools/tree/main/.opencode/skills/ce-session-inventory
Command: npx skills add https://github.com/thisisryanswift/zellij-agent-tools --skill ce-session-inventory

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This skill helps agents locate and report session files across Claude Code, Codex, and Cursor, and produce structured metadata to support session research.

Core Features & Use Cases

  • Discover session files across Claude Code, Codex, and Cursor.
  • Emit JSONL with per-file session metadata, including platform, session, file, size, ts, and last_ts where available.
  • Output a final _meta line with counts and parse errors to support robust downstream processing.
  • Use Case: Researchers can quickly analyze session history without needing to know on-disk layouts.

Quick Start

Run the discover-sessions.sh script with your repo name and a days window to generate per-file session metadata.

Frequently Asked Questions about ce-session-inventory

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

FAQPage Schema
How do I discover session files across Claude Code, Codex, and Cursor?

You can discover session files across Claude Code, Codex, and Cursor by running the discovery script, which scans a repo within a specified days window and identifies recent session records across all supported platforms.

Can I filter session metadata discovery by a specific platform?

Yes, you can apply an optional platform filter to limit session metadata discovery to Claude Code, Codex, or Cursor individually, or scan all platforms simultaneously within your given days window.

What format does session metadata extraction output?

Session metadata extraction outputs JSONL format, emitting one JSON object per session with fields like platform, session, file, size, ts, and last_ts, followed by a final _meta line containing counts and parse errors.

How do I extract session metadata for research without knowing on-disk layouts?

You can extract session metadata without knowing on-disk layouts by running the discovery script against your repo, which automatically locates session files and emits structured JSONL metadata for downstream research analysis.

Does session discovery work across multiple coding platforms at once?

Yes, session discovery works across Claude Code, Codex, and Cursor simultaneously, enumerating recent sessions within a given days window and reporting per-file metadata including timestamps and file sizes for each platform.

What information is included in the final meta line of session metadata output?

The final _meta line in session metadata output includes total session counts and parse errors, providing a summary that supports robust downstream processing and validation of the extracted session records.