session-analyzer
Analyze a Claude Code or Claude Desktop agent-mode session transcript (JSONL) and produce a structured Markdown report. The report covers: all tool calls and their types, attribution of each action to a skill/agent rule vs. LLM autonomous decision, steps that caused errors and how the LLM recovered, total token usage and estimated cost, and optimization recommendations. Trigger when the user asks to "review", "analyze", "audit", or "report on" a Claude session, mentions a session directory path, a session UUID, an `audit.jsonl` / Claude Desktop log, or asks things like "what happened in that session", "what did Claude do in that run", "how many tokens did it use", "why did it retry", "what errors occurred", or "show me the tool calls". Also trigger when the user says "session report", "session summary", or references a session file by path or ID.
Target: AI & workflow automation. Automatically collected · unverified.
Excerpt from the author’s documentation
Extracted from a fixed version of SKILL.md in its original language. This is the author’s documentation; installation, compatibility and runtime results have not been verified by this site.
Read the original English text
Topics in the source
- 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
This is an excerpt. Refer to the complete source and its current requirements.
- Source repository
- svd/agent-skills
- Source file
- plugins/session-analyzer/skills/session-analyzer/SKILL.md
- Fixed revision
- cb47e43decd9132b8b9ffc29a43960cc5724435e
Sources and evidence
This record was collected automatically. Its documentation, suitability and runtime behavior have not been manually verified.
Author: svd/agent-skills · original repository metadata. Documentation review: Not reviewed. Last source check: 2026-11-11T00:00:19.072Z.
Categories are inferred from names, descriptions and paths. They do not establish compatibility.
License and attribution
MIT. Third-party content and copyright remain with their authors. Refer to the original license and terms.
Original license ↗Synchronization, copying and user-reported success do not mark a resource as runtime-tested.
Limitations and notes
- Collecting metadata does not mean this site has installed, adapted, runtime-tested or security-reviewed the resource.