se-session-inventory

Emit structured JSON metadata for session files across Claude Code, Codex, and Cursor.

Updated May 7, 2026
One-click install
npx skills add https://github.com/simonwjackson/pi-software-engineering --skill se-session-inventory
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: se-session-inventory
Source: https://github.com/simonwjackson/pi-software-engineering/tree/main/skills/se-session-inventory
Command: npx skills add https://github.com/simonwjackson/pi-software-engineering --skill se-session-inventory

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps teams locate session files within a repository and extract structured metadata (timestamps, branch, cwd, size, platform) so researchers and agents can analyze session history without manual digging.

Core Features & Use Cases

  • Cross-platform discovery: index session stores across Claude Code, Codex, and Cursor.
  • Metadata extraction: emit per-session fields such as ts/last_ts, session, branch, cwd, and size for correlation across platforms.
  • Batch and single-file processing: support scalable scans and precise, targeted investigations for individual sessions.
  • Use Case: researchers can quickly assemble a cross-platform view of session activity to identify trends or anomalous work patterns.

Quick Start

Scan a repository to enumerate session files and extract their metadata across Claude Code, Codex, and Cursor.

Frequently Asked Questions about se-session-inventory

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

FAQPage Schema
How do I extract session metadata from Claude Code, Codex, and Cursor?

To extract session metadata, you can scan a repository to discover JSONL session stores across Claude Code, Codex, and Cursor. This process emits structured JSON objects containing per-session fields like ts/last_ts, session, branch, cwd, and size.

What is the best way to index session files across multiple AI coding platforms?

Indexing session files across multiple AI coding platforms is best handled by cross-repo discovery tools that read JSONL session stores. This approach aggregates per-session metadata like timestamps, branch, and cwd into structured JSON objects for analysis.

Can I analyze session history from Cursor alongside Claude Code sessions?

Yes, you can analyze session history from Cursor alongside Claude Code sessions. Cross-platform discovery reads JSONL session stores from both tools to emit structured metadata, enabling researchers to correlate activity and identify trends.

Does session file discovery support batch processing for multiple repositories?

Session file discovery does support batch processing for multiple repositories. It includes scalable scanning logic to enumerate session files and extract metadata across platforms, accommodating both batch and single-file investigations.

What metadata fields are available when extracting Claude Code session history?

When extracting Claude Code session history, available metadata fields include ts, last_ts, session, branch, cwd, and size. These fields are emitted as structured JSON objects for each discovered session file.