{"version":"2.1.323","anchor":"auto-mode-subagent-warning-prefix-is-now-a-shared-constant","canonical_anchor":"auto-mode-subagent-warning-prefix-is-now-a-shared-constant","heading":"Warning text on blocked helper-agent reports now comes from a shared value","tier":"internal","area":"Auto Mode","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.323\/e\/auto-mode-subagent-warning-prefix-is-now-a-shared-constant","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.323","markdown":"### Warning text on blocked helper-agent reports now comes from a shared value\n\nThe \"SECURITY WARNING\" start of the auto mode message about a blocked helper-agent report now comes from a shared value\n\n**What**\n\nIn auto mode, Claude can act without asking you first, and it can hand work to a subagent, which is a helper agent that does part of a task. When auto mode blocks a subagent's report, the warning message used to begin with a fixed \"SECURITY WARNING:\". That opening now comes from a value shared with other parts of Claude Code. The rest of the message is unchanged.\n\n**Why**\n\nThe opening words of this warning may now read differently from \"SECURITY WARNING:\".\n\n- Area: Auto Mode\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 0\/5\n- Scope: individual\n- Heads-up: no"}