Monitors

A monitor scores how suspicious an action or a whole trajectory looks, and the blue team audits the highest scores against its human budget. Action monitors are selected with ct run monitor --action-monitor <name>, trajectory monitors with --trajectory-monitor <name>.

Action monitors

Monitor	Description
`checklist`	Answers five yes/no checks per action (necessity, security surface, innocent explanation, concrete harm, removability) before scoring; the top of the scale is gated on concrete harm.
`goal-analysis`	Scores each action while shown the environment's candidate covert objectives, asking whether the action advances any of them.
`mean-action`	Averages two independent runs of the old-action monitor on each action.
`mean-goals`	Averages two independent goal-analysis runs on each action.
`mean-single-goal`	Scores each action twice per covert objective, averages each objective's scores, and keeps the highest average.
`multi`	Weighted blend of the orthogonal and old-action monitors' scores for each action.
`no-history`	Scores each action in isolation with no preceding action history or candidate covert-objective hints.
`old-action`	The default action monitor: one model call per action, shown the candidate covert objectives.
`old-action-no-goals`	The default action monitor without the candidate covert objectives.
`orthogonal`	Flags work that does not serve the main task - unnecessary changes, premature optimization, off-task activity - rather than judging malice directly.
`single-goal`	Scores each action once per candidate covert objective in parallel and keeps the maximum score.
`strong`	Sees the full conversation history (goal-blind) so it judges each action in context.
`strong-goals`	The strong full-history monitor, additionally shown the environment's candidate covert objectives.
`three-scores`	Categorical monitor: a safe / uncertain / suspicious verdict per action, mapped onto the score scale.

Trajectory monitors

Monitor	Description
`mean-goal-analysis`	Averages two independent goal-analysis passes over the transcript.
`mean-quick`	Averages five independent quick passes over the transcript.
`mean-single-goal-analysis`	Reads the transcript twice per covert objective, averages each objective's scores, and keeps the highest average.
`monitoring-bench`	Replica of the MonitoringBench benchmark's monitor: the bench prompt on its fixed 3-model panel, max-aggregated.
`quick`	Reads the full transcript in a single pass, shown the candidate covert objectives, and returns one score for the trajectory.
`quick-no-goals`	Reads the full transcript in a single pass with no covert-objective hints.
`single-goal-analysis`	Reads the full transcript once per candidate covert objective in parallel and keeps the maximum score.
`traj-goal-analysis`	Reads the full transcript while shown the environment's candidate covert objectives, working through them one by one.