{"version":"2.1.227","anchor":"task-tool-is-stricter-about-when-to-run-an-agent-in-the-fore","canonical_anchor":"task-tool-is-stricter-about-when-to-run-an-agent-in-the-fore","heading":"Task tool is stricter about when to run an agent in the foreground","tier":"notice","area":"Subagents","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.227\/e\/task-tool-is-stricter-about-when-to-run-an-agent-in-the-fore","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.227","markdown":"### Task tool is stricter about when to run an agent in the foreground\n\nClaude keeps subagents in the foreground only when the very next step needs their answer.\n\n**What**\n\nThe guidance for launching a subagent used to say run it in the foreground whenever you need the result before proceeding. It now limits that to cases where the very next action depends on the result and nothing else could usefully happen in the meantime, and names fire-and-forget work and independent investigations as background cases.\n\n**Evidence**\n\n`Wanting the result \"next\" is not enough on its own.`\n\n- Area: Subagents\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 2\/5"}