{"version":"2.1.251","anchor":"subagents-can-start-without-a-prompt-when-every-url-in-them-","canonical_anchor":"subagents-can-start-without-a-prompt-when-every-url-in-them-","heading":"Subagents can start without a prompt when every URL in them is already allowed","tier":"notice","area":"Permissions","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.251\/e\/subagents-can-start-without-a-prompt-when-every-url-in-them-","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.251","markdown":"### Subagents can start without a prompt when every URL in them is already allowed\n\nSubagents launch without a prompt when every URL in them is already allowed.\n\n**What**\n\nLaunching a subagent no longer asks for confirmation when the agent type is active and every URL mentioned in its prompt would already be allowed by the WebFetch permission rules. If any URL is not already permitted, or the prompt carries too many of them, you get the usual permission prompt.\n\n**Details**\n\n- only applies in permission modes that would otherwise require an explicit confirmation for the launch\n- each URL is run through WebFetch's own permission check and must come back as allowed\n- two internal conditions disable the shortcut entirely, in which case launches always prompt\n\n**Evidence**\n\n`this approval was already used by an earlier attempt`\n\n- Area: Permissions\n- Tier: You'll notice\n- Useful: 4\/5\n- Signal: 3\/5"}