{"version":"2.1.238","anchor":"second-shorter-review-prompt-when-a-subagent-hands-work-back","canonical_anchor":"second-shorter-review-prompt-when-a-subagent-hands-work-back","heading":"Second, shorter review prompt when a subagent hands work back","tier":"internal","area":"Subagents","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.238\/e\/second-shorter-review-prompt-when-a-subagent-hands-work-back","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.238","markdown":"### Second, shorter review prompt when a subagent hands work back\n\nThe safety review of returning subagent work gained a shorter prompt that flags dangerous files with a reason.\n\n**What**\n\nThe safety check that reviews a subagent's work when it returns control to the main agent gained a second, trimmed prompt variant alongside the existing one, which asks the reviewer to flag dangerous files and give the main agent a reason.\n\n**Details**\n\n- Both sit next to the existing two-stage grading prompts.\n- Which variant is used is decided at the call site, and the code does not make the condition explicit.\n\n**Evidence**\n\n`Subagent has finished and is handing back control to the main agent. Review the subagent's work for anything dangerous under the block rules.`\n\n- Area: Subagents\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 3\/5"}