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 v2.1.299 ·

UserPromptSubmit hooks get more detail about the prompt

Information prepared for UserPromptSubmit hooks now includes the command and whether the prompt is an internal one

You'll notice Improvements
JSON All of v2.1.299
You'll noticeTier: how much it should matter to you
2Useful: my rating, 1 to 5
1Signal: worth watching, 1 to 5
HooksArea: what it touches
ImprovementsKind: in v2.1.299,
ImprovementsSection of the release

Unclear It is not confirmed that command and isMeta reach the input your hook script receives.

What

A UserPromptSubmit hook is a command you set to run when a prompt is submitted, before Claude works on it. Claude Code has changed how it handles these:

  • The information prepared for the hook now includes command and isMeta, taken from the submitted prompt.
  • When a prompt is blocked because the hooks never ran, the block now carries a reason saying so.
  • Warnings now say whether the prompt was kept.
Why

Hooks can tell apart prompts that come from a slash command or from Claude Code itself, rather than from what you typed.

Read from
Names in the bundleUserPromptSubmit
Since it was published

The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.

Confirmed since Anthropic's documentation has since written up UserPromptSubmit, on Intercept and control agent behavior with hooks. * `UserPromptSubmit` and [`UserPromptExpansion`](/docs/en/hooks#userpromptexpansion): Claude Code blocks the prompt with a message naming the hook and the timeout, and the session continues. Before v2.1.208, Claude Code ended the query wit… agent-sdk/hooks see the edit
How sure we are
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubtIt is not confirmed that `command` and `isMeta` reach the input your hook script receives.
Anthropic's documentation agreesAnthropic's documentation has since written up UserPromptSubmit, on Intercept and control agent behavior with hooks.
Anthropic's release notes agreeFixed Edit and Retry in Cowork and claude.ai cloud sessions failing on a message stopped while its UserPromptSubmit or mod prompt.submit…

See this entry in the whole of v2.1.299 →

Feedback