{"version":"2.1.237","anchor":"new-built-in-output-style-concise","canonical_anchor":"new-built-in-output-style-concise","heading":"New built-in output style \"Concise\"","tier":"use","area":"Output Styles","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.237\/e\/new-built-in-output-style-concise","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.237","markdown":"### New built-in output style \"Concise\"\n\nYou can now pick a \"Concise\" output style so Claude leads with results and skips narration.\n\n**What**\n\nA fifth built-in style joins Proactive, Explanatory and Learning. Described as \"Claude responds tersely, leading with results and skipping preamble and narration\", it tells the model to lead with the result, cut narration, answer simple questions in 1-3 sentences and never trade correctness for brevity. Nothing gates its registration, so anyone on this build can pick it from the output-style list unless output styles are turned off entirely.\n\n**Details**\n\n- Registered as a built-in style with coding instructions retained, so normal engineering guidance still applies.\n- Its system prompt is headed \"# Concise Style Active\" and states explicitly that it overrides more general communication guidance, backed by six rules plus a short reminder re-injected each turn.\n- Reported in prompt telemetry under its own key rather than collapsing into the generic one.\n\n**Evidence**\n\n`Claude responds tersely, leading with results and skipping preamble and narration`, `The user chose brevity over narration. You should:`\n\n- Area: Output Styles\n- Names: `\/output-style`\n- Tier: Use it now\n- Useful: 4\/5\n- Signal: 2\/5"}