{"version":"2.1.163","anchor":"subagentstop-hook-event","canonical_anchor":"subagentstop-hook-event","heading":"SubagentStop Hook Event","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.163\/e\/subagentstop-hook-event","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.163","markdown":"### SubagentStop Hook Event\n\n**What**\n\nA new hook event fires when a subagent finishes, complementing the existing `Stop` event which fires when the main conversation agent finishes. The hook output's `additionalContext` field is delivered back to the subagent so it can continue and act on the feedback.\n\n**Details**\n\n- Event name: `SubagentStop`\n- Available for command-based and prompt-based hooks\n- Hook output schema: `{ hookEventName: \"SubagentStop\", additionalContext?: string }`\n- `additionalContext` is non-error feedback; the subagent continues execution so it can act on it\n- Prompt-based hooks now also explicitly support `SubagentStop` alongside `Stop`, `UserPromptSubmit`, and `PreToolUse`\n\n**Evidence**\n\nSchema literal for the new event (search for `\"Hook-specific output for the SubagentStop event\"`)"}