What asks for your approval
Claude Code and Codex never ask before using their own tools, such as their shell and file editing: Clawboo runs them with their own approval prompts turned off. Hermes asks only before the commands its own policy flags; its other tools, file editing included, run without asking. Their connector calls and hand-offs still follow the rules above. See Hermes. What agents can do explains what they can reach. Command permissions sets when the two shell checks ask, and Connectors lists which connector calls ask.
The risky-word check matches whole words, in any letter case:
- delete, destroy, deploy, publish, release, secret, credential, prod, production
- the phrases drop table and rm -rf
- api_key, api-key or apikey, and force-push, force_push or forcepush
Where approvals appear
- Needs you on the Board, the first column. It shows requests for the teams in the board’s filter, plus Boo Zero’s requests and any request Clawboo cannot tie to an agent.
- The chat, in a tray above the message box. A team chat shows that team’s requests, and a one-to-one chat shows that agent’s. The tray holds three cards, then a +N more, view on the board link.
- The Tasks card beside a team chat and the Tasks & Routines card on an agent’s page, under Needs you.
- Settings > Insights > Governance, in the Approval queue. It lists every pending request from every team, or “No pending approvals”.
- Settings > Workspace > Capabilities, at the top of the panel, while something is waiting.
- A browser alert, when you have turned alerts on and the Clawboo tab is in the background. Click it to open Needs you on the board. See Get an alert outside the tab.
Read a card
Requests appear on two kinds of card.Command cards on the Board and in chat
On the Board, in the Tasks cards and in the chat tray, an OpenClaw agent’s command appears on a command card:- Wants to run a command with the agent’s Boo and name, or in the chat tray an Exec Approval label (with the agent’s name in a team chat).
- expires Ns: roughly how long is left.
- The command, cut off after about two lines.
- An error line, when your last answer did not go through.
- Three buttons: Allow Once, Always and Deny.
Request cards
Every other request uses a request card, and so does every request in the Governance and Capabilities queues, OpenClaw commands included. A request card shows:- For a call to an app reached through Composio, the app’s logo and name. Otherwise the agent’s name, or Waiting on you when Clawboo cannot tell which agent asked.
- A short label for the kind of action, such as Runs a command, Reads only or Acts on your Gmail, and the seconds left.
- One sentence naming the agent and what it wants, such as “Ada wants to run a command on this computer.”
- The details that decide the answer, such as the recipient, the file or the command: two on the Board and in chat, three in the queues. A Show N more details link opens the rest, including any note the agent gave, which Clawboo marks as not verified.
- On some cards, a checkbox that remembers your answer (see Answer a request).
- An allow button named for the action, such as Run it, Allow read, Send it or Delete it (otherwise Allow), and Don’t allow.
Answer a request
A few details decide what you see:
- Always on the Board and in chat. The command card offers Always every time. When the Gateway does not accept it for that command, for example because the agent is set to Always Ask, the card shows an error. Choose Allow Once or Deny instead.
- The 30-day box on connector cards. It appears only when the call was made under access you shared with the agent, Clawboo could read the request, and the call is not one that must ask every time. A call to a destructive tool is one of those, so it never offers the box. Access set through the API to ask on every call (
approvalPolicy: always) never offers the box. Neither does a run that has read private data and also taken in outside content: it asks before any call that could send data out. - Hand-offs in a row. A leader’s hand-offs in one turn start one after another, so the hand-offs after a risky one wait for your answer too.
What Always remembers
- An OpenClaw command. The Gateway lets that agent run the command in that folder without asking, with no end date. To take it back, open the agent’s page, then Details > Permissions, and revoke it under Commands this Boo can run without asking (see Command permissions). Revoking does not undo a command that already ran.
- A connector tool. Clawboo stops asking about that tool, with any arguments, for 30 days, for the access you shared with that agent. That includes calls that change something outside Clawboo. A call to a destructive tool still asks every time, even with an answer on file, and so do calls that must always ask. Access set to ask on every call (
approvalPolicy: always) asks even for a tool you answered Always before it was set that way. To end it early, stop sharing the connector with the agent on the graph (Connectors). Sharing it again starts with nothing remembered. Answers remembered by an earlier version of Clawboo, when Always did not stop the prompt on a call that changes something, are cleared once on the first start after you upgrade. - A risky hand-off. Nothing is remembered. An answer of
allow_alwayssent through the API allows that one hand-off, and the next risky hand-off asks again.
If nobody answers in time
The card goes away and Clawboo records the request as expired, not as a refusal. Then:- OpenClaw command. Clawboo’s server keeps a copy of each request, so the card waits for you even while no browser tab is open. If an open tab received the request live, the agent’s one-to-one chat in that tab also notes that the approval timed out.
- Clawboo Native command. The command does not run, and the agent cannot ask about another one for the rest of that run. The run waits while the card is open.
- Hermes command. Hermes denies the command when its own wait ends (300 seconds by default) and the run carries on. The run waits while the card is open.
- Connector call. The call is refused.
- Risky hand-off. The hand-off is skipped and the leader is told. When the hand-off came from a task, that task gets the comment
Delegation to <name> not approved (<reason>); skipped.
What a card does not show
- The folder, on the Board and in chat. A command card there shows only the command, and cuts a long one off. Open the Approval queue in Governance to see the full command and its folder.
- Why the agent wants it. No card shows an agent’s reason for a command, even when it gave one.
- Every field at once. A request card shows the deciding fields first. The rest, and any note from the agent, are behind Show N more details.
- Secrets. Values that look like passwords or keys are masked.
- An exact countdown. The seconds left are worked out when the card is drawn, so treat them as approximate.
- Past answers. The dashboard keeps no list of requests you already answered, but the Activity feeds show each request and its answer by tool name. The audit log in Governance records risky hand-off decisions.
Check that it worked
- The card leaves Needs you, the chat tray and the queues. When nothing is left, Needs you reads “Nothing needs you right now”.
- An allowed command runs and the agent carries on. After Always, if the command’s output does not reach the chat, Clawboo asks the agent to run it again so you see the result. The command is on the agent’s list by then, so no new card appears. After Allow Once Clawboo does not do this; if no output appears, ask the agent to run the command again.
- A refused or expired hand-off leaves the “not approved” comment on the task it came from.
- On the Org chart and team graphs, an OpenClaw agent with a command waiting shows a pulsing amber ring. The ring appears only for requests this browser tab received while it was open.
Troubleshooting
A card disappeared before I answered
A card disappeared before I answered
It ran out of time. The waits are in What asks for your approval. For OpenClaw agents that ask too often, set Command Execution to Ask for Unknown, so only commands the agent is not already allowed to run ask. See Command permissions.
I pressed Always and the card shows an error
I pressed Always and the card shows an error
The Gateway did not accept Always for that command. An agent set to Always Ask never remembers a command, and the Gateway can refuse it for other commands too. Press Allow Once or Deny, or change the agent’s Command Execution setting first.
I allowed a command but its output never appeared
I allowed a command but its output never appeared
After Allow Once, Clawboo does not ask the agent to repeat the command, and the Gateway may not send the output to the chat. Ask the agent to run the command again.
clawboo could not reach the Gateway to send that decision.
clawboo could not reach the Gateway to send that decision.
Your tab has no connection to the OpenClaw Gateway, and Clawboo’s server could not pass your answer on either. Check that OpenClaw is connected under Settings > Workspace > Runtimes, then answer again before the card expires.
An agent ran a command without asking me
An agent ran a command without asking me
Claude Code and Codex never ask before a command, and Hermes asks only before the commands its own policy flags (set
approvals.mode in your own ~/.hermes/config.yaml to change which, unless agents run as their own user). An OpenClaw agent runs without asking when it is set to Run Freely, or when the command is already on its list under Commands this Boo can run without asking. A Clawboo Native agent asks before every command.clawboo could not tell which agent asked for this.
clawboo could not tell which agent asked for this.
The request arrived with no agent identity, which is how connector calls from OpenClaw agents arrive. Decide from the details on the card. The card appears in every chat and under every board filter.
A leader is waiting, but I see no card
A leader is waiting, but I see no card
Set the board’s team filter to All teams, or open the Approval queue in Governance, which lists every pending request. A risky hand-off waits only 5 minutes, so it may have expired already.
Under the hood
Under the hood
- OpenClaw requests. Clawboo’s server keeps its own connection to the Gateway and copies each command request into Clawboo’s tool-call approvals table as a row of kind
exec, keyed by the Gateway’s id. Every 30 seconds it marks rows past their deadlineexpired, neverdeny, and writes no audit row for them. - Answers. A tab with its own Gateway connection sends the answer straight to the Gateway (
exec.approval.resolve). Every other answer goes throughPOST /api/tools/approvals/:id/resolve, which answers the Gateway first for anexecrow. That route takes an answer only from the dashboard’s page or a person a sign-in proxy vouched for (see the person check); anything else gets403, so an agent cannot answer a card by accident. On your own computer that is a speed bump: an agent running as you can send the same headers. - Which task. Each card records the task its run works on: a connector call’s from the run’s signed Tools URL, a Clawboo Native command’s and a risky hand-off’s from the run itself, and an OpenClaw command’s from the session it came from. A card from a 1:1 chat or a lead’s own turn has none, and neither does an OpenClaw agent’s connector call, because the Tools address OpenClaw shares among its agents carries no task. Answering twice is safe: the second answer changes nothing.
- Hermes requests. Each
approval.requeston a Hermes run’s event stream becomes a row of kindhermes(toolrun_command, never remembered). An answer goes to Hermes first, asPOST /p/<profile>/v1/runs/<run>/approvalwithonceordeny, and the row changes once Hermes took it. A card left open when Clawboo stops expires at the next start. - Clawboo’s own requests. Connector calls, Clawboo Native commands and risky hand-offs are rows in the same table, and the dashboard checks for new ones every 3 seconds. Clawboo records answers as
allow_once,allow_alwaysanddeny; OpenClaw’s words areallow-once,allow-alwaysanddeny. - Remembered answers. A connector Always writes a standing rule bound to the access you shared, expiring after 30 days, and stopping the share deletes its rules. A risky hand-off is filed per leader under the scope
delegate:codeand marked never-remember, so every one raises a card. - Cleanup. A connector call, Clawboo Native command or risky hand-off marks its own request
expiredas soon as it stops waiting. Once an hour, Clawboo also expires any request still pending afterCLAWBOO_APPROVAL_TTL_MS(24 hours by default), such as one left open when Clawboo stopped. That cleanup does not lengthen the waits on this page. - Event log. Every request writes an
approval_requestedevent and its answer or expiry anapproval_resolved, without the arguments or the command. A connector call, Native command or hand-off left open when Clawboo stopped writes itsapproval_resolvedwhen someone tries to answer it, or when the hourly cleanup expires it 24 to 25 hours after it was created. See Approval events. - History.
GET /api/approvals?agentId=<id>lists the OpenClaw command decisions made from tabs with a Gateway connection, newest first. - Shapes and codes: Governance API and Tools and MCP API. Every waiting time is in Limits and defaults.
Next steps
- Command permissions: choose when OpenClaw and Clawboo Native agents ask, and revoke what Always allowed.
- Connectors: share connectors with agents and see which calls ask.
- What agents can do: what each runtime can reach without asking.
- Budgets and guardrails: the risky hand-off check and the other limits on agents.
- Board: everything else that waits in Needs you.