session-analyzer

原文涵盖的主题

• Session Analyzer
• Step 1 — Resolve the session
• Step 2 — Parse the session
• Desktop-only totals fields
• Workflows (the Workflow tool)
• Teammate sessions (the Agent tool's second spawn mode)
• Step 2.5 — Desktop: one report per run (skip when format is claude-code)
• Step 3 — Determine report filename

Produces a structured Markdown report from a Claude session transcript — either a Claude Code JSONL transcript or a Claude Desktop agent-mode audit.jsonl log. Format is auto-detected; the report structure is identical either way. Report filename is chosen interactively (default: session-report- .md). The user provides one of: Claude Code — filesystem path — a directory containing .jsonl, or a direct .jsonl file path. Claude Code — session UUID — a 36-char UUID like 7d6b74af-3bfb-4447-bebe-bb3aa141a12d. Search /.claude/projects// .jsonl. Claude Desktop — path — a direct path to an audit.jsonl file, or a local conversation directory containing one. Format is detected structurally (not by path shape), so a copied-out log with a different filename still works. Claude Desktop — discovery — if the user doesn't have a path, run python3 "$CLAUDEPLUGINROOT/scripts/parsesession.py" --list-desktop [--root ] to list conversations under the two standard macOS roots (/Library/Application Support/Claude and .../Claude-3p). Pass --root for any additional Desktop instance (e.g. one launched with a custom --user-data-dir) — never assume a fixed root beyond the two standard ones; ask the user for it

这里只展示节选，请以完整原文和当前要求为准。