Follow Discord
Sweep 22 Oct 2026 · 04:32Z Build v2.1.308 527 read Stable v2.1.308 Latest v2.1.308 Next v2.1.308 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.300 ·

Prompts that hooks neither allow nor block are now recorded as having no verdict

When 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

Under the hood Internal Changes
JSON All of v2.1.300
Under the hoodTier: how much it should matter to you
1Useful: my rating, 1 to 5
1Signal: worth watching, 1 to 5
HooksArea: what it touches
Internal ChangesKind: in v2.1.300,
Internal ChangesSection of the release
What

Hooks 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:

  • The prompt hooks gave no decision.
  • The run was cut short.
  • A slash command whose handling was put off was passed along.

These 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.

Why

This 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.

See this entry in the whole of v2.1.300 →

Feedback