Dangerous mode
Normally an agent asks before doing something risky — running a command, editing a file. Dangerous mode switches those questions off, so the agent works without stopping.
1/3Normally the agent stops and asks before running a command.
Turn it on
Open the agent card’s ⋯ menu and choose Enable dangerous mode. An amber triangle appears in the card’s header, and the mode takes effect the next time the agent starts. The setting is per card — it never applies to all agents at once. Disable dangerous mode in the same place turns it off.
In dangerous mode the agent can delete files and run any command without asking. Use it on a project you have backed up, ideally together with an isolated worktree and a budget.
Kilo Code and Pi don’t offer this mode. Plain terminals don’t need it.