{"version":"2.1.300","anchor":"prompt-submit-pipeline-records-a-no-verdict-outcome","canonical_anchor":"prompt-submit-pipeline-records-a-no-verdict-outcome","heading":"Prompts that hooks neither allow nor block are now recorded as having no verdict","tier":"internal","area":"Hooks","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.300\/e\/prompt-submit-pipeline-records-a-no-verdict-outcome","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.300","markdown":"### Prompts that hooks neither allow nor block are now recorded as having no verdict\n\nWhen prompt hooks give no decision, the run is cut short, or a slash command is handed on, the prompt is now marked as having no verdict\n\n**What**\n\nHooks are your own scripts that Claude Code runs at set moments, including when you submit a prompt. Such a hook can let a prompt through, block it, or rewrite it. Claude Code now marks a submitted prompt as having \"no verdict\" in these cases:\n\n- The prompt hooks gave no decision.\n\n- The run was cut short.\n\n- A slash command whose handling was put off was passed along.\n\nThese cases are now kept apart from prompts that were dropped or rewritten. Prompts that hooks checked are also reported through a recording step instead of a plain notice.\n\n**Why**\n\nThis changes how prompts checked by hooks are counted in remote sessions and in sessions driven by the Agent SDK, the toolkit for running Claude Code from your own program.\n\n- Area: Hooks\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}