agent-autopsy
Reconstruct a completed, failed, expensive, or confusing agent session to find where its trajectory broke and what one change would prevent recurrence. Use when investigating post-hoc session diagnosis, tool-loop analysis, goal drift, premature completion, or repeated human rescue. Do not use as employee performance scoring.
- License
- MIT
Pinned to revision 43d6362088ba, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/agent-autopsy/SKILL.md
- skills/agent-autopsy/agents/openai.yaml
- skills/agent-autopsy/evals/cases.json
- skills/agent-autopsy/references/failure-taxonomy.md
- skills/agent-autopsy/scripts/session_stats.py
Every link opens the file at its source, pinned to the revision this page describes.