Session inventory

Agent-facing primitive. Discover session files and emit session metadata as JSONL across Claude Code, Codex, and Cursor.

This skill exists so that agents researching session history do not need to know the layout of session stores on disk or the JSONL shapes of each platform. The scripts under scripts/ own that knowledge.

Arguments

Space-separated positional args:

1. <repo> — repo folder name (e.g., my-project). Used for directory matching in Claude Code and Cursor, and as the CWD filter for Codex sessions.
2. <days> — scan window in days (e.g., 7). Session files older than this are skipped.
3. <platform> (optional) — one of claude, codex, cursor. Omit to search all three.
4. --keyword K1[,K2,...] (optional) — filter to sessions whose full file content matches at least one of the comma-separated keywords (case-insensitive substring). Each emitted session line gains match_count and keyword_matches ({K: N, ...}) fields, and the _meta line gains files_matched. Use this instead of rolling per-file grep -l calls when ranking many sessions by topical relevance.

Execution

Run the discovery-plus-metadata pipeline from the skill's own scripts/ directory: