Reading a Recorded Agent Run

A recording is evidence. Your memory of a session is not, and neither is a transcript you were handed — both are missing the tool results, the exit codes, and the files that changed without anyone mentioning them.

The rule: when a question is about something that already happened, read the trace before you answer. Do not reconstruct it. If a recording exists, guessing is the wrong move even when the guess would have been right.

This skill does not drive the agent — it reads what an earlier one did. Pair it with whatever harness produced the run: Claude Code, Codex, opencode, Cursor, or a framework agent recorded with orca record generic-openai -- <cmd>.

When to use