On this page
On this page
Agent coordination
Steer
/steer first tries to send guidance to an already-active run. It is for
"adjust this run while it is still working" moments. If the current runtime
cannot accept steering, OpenClaw sends the message as a normal prompt instead
of dropping it.
/tell is an alias of /steer. The two names are interchangeable everywhere
on this page.
Current session
Use top-level /steer to target the active run for the current session:
Behavior:
- Targets only the current session's active run.
- Works independently of the session's
/queuemode. - Starts a normal turn with the same message when the session is idle or the active run cannot accept steering.
- Uses the active runtime's steering path, so the model sees the guidance at the next supported runtime boundary.
With an explicit messages.queue.allowCollaborativeSteering: false and quiet fallback selected, steering another person’s
active turn queues quietly as a separate turn under the sender’s identity and
current policy. Set messages.queue.collaborativeSteeringFallback: "reject" to
refuse instead and offer /followup <message> for an explicit separate turn. This applies to /steer and
/tell as well as ordinary steering input. See Steering scope.
One message as a new turn
Use /followup <message> when this message should start a separate turn instead
of changing work in progress:
When the session is busy, the message waits behind current and already-queued
work. When it is idle with no queued work, normal admission starts it immediately.
It does not answer a pending question, join a collect batch, or change the saved
/queue mode. The new turn keeps its submitter and uses the policy applicable
when it is admitted.
OpenClaw reports whether the message was queued, started, or rejected. A queued
notice means the message entered the queue, not that it changed the active run.
Queue capacity and cancellation still apply. This command also works in
openclaw chat and openclaw tui --local.
Steer vs queue
/queue steer makes normal inbound messages try to steer the active run when
they arrive while a run is active. /steer <message> is an explicit command
that tries to inject that command's message into the active run at the next
supported runtime boundary, regardless of the stored /queue setting. When
that injection is not available, the command prefix is stripped and <message>
continues as a normal prompt.
The explicit /steer (and /tell) command is Gateway-backed. In
openclaw chat or openclaw tui --local, select /queue steer and send the
guidance as a normal message; the embedded runtime applies the same steering
policy without forwarding a Gateway command.
Use:
/steer <message>when you want to guide the active run right now./followup <message>when only this message should wait for its own turn./queue steerwhen you want future normal messages to steer active runs by default./queue collector/queue followupwhen future normal messages should wait for a later turn instead of steering the active run./queue interruptwhen the newest message should replace the active run instead of steering it.
For queue modes and steering boundaries, see Command queue and Steering queue.
Sub-agents
Top-level /steer targets the current session's active run. Sub-agents report
back to their parent/requester session; /subagents is for visibility only.
ACP sessions
Use /acp steer when the target is an ACP harness session:
ACP harness sessions cannot accept input mid-turn. /acp steer queues the
instruction and runs it after the active turn finishes; use /acp cancel first
to stop work in progress. See ACP controls.
See ACP agents for ACP session selection and runtime behavior.
