{"version":"2.1.239","anchor":"optional-send-a-one-line-outcome-before-stopping-instruction","canonical_anchor":"optional-send-a-one-line-outcome-before-stopping-instruction","heading":"Optional \"send a one-line outcome before stopping\" instruction","tier":"use","area":"Terminal UI","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.239\/e\/optional-send-a-one-line-outcome-before-stopping-instruction","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.239","markdown":"### Optional \"send a one-line outcome before stopping\" instruction\n\nTurn on agentPushNotifEnabled and Claude sends a one-line outcome before stopping; off by default.\n\n**What**\n\nWhen the `agentPushNotifEnabled` setting is on, an extra line is added to the prompt asking Claude to send a one-line outcome before it stops, on the grounds that you may be away and waiting to hear it is done, unless you just told it to stop. The setting falls back to false, so the line is absent by default.\n\n**Details**\n\n- The fragment returns an empty string unless both an internal check and the `agentPushNotifEnabled` setting pass.\n\n**Evidence**\n\n`the user may be away and waiting to hear it's done`\n\n- Area: Terminal UI\n- Names: `agentPushNotifEnabled`\n- Tier: Use it now\n- Useful: 3\/5\n- Signal: 4\/5\n- Present in the build but not switched on"}