Use when debugging or auditing another Claude Code session, investigating what a prior agent did or left behind, reconstructing a failure that hit an earlier session, finding the cause of mystery state in a project (orphan processes, dirty files, broken hooks), or building context before continuing
Use when debugging or auditing another Claude Code session, investigating what a prior agent did or left behind, reconstructing a failure that hit an earlier session, finding the cause of mystery state in a project (orphan processes, dirty files, broken hooks), or building context before continuing someone else's work