Unclear Whether Claude Code sends these details by default is not clear.
What
A hook is a command you or a plugin set up to run automatically at certain moments, for example PreToolUse, which runs before Claude uses a tool and can block it. When a hook decides whether Claude may go ahead, Claude Code can now record three extra details:
- The hook event,
PreToolUseortool.check. - The hook's source: your settings, a plugin, or a skill, with its name where there is one.
- For a plugin, its ID in the form
plugin@marketplace.
The source and plugin ID are checked against these expected forms.
Why
These look like telemetry fields, meaning usage data, that would show which hook decided a permission outcome.
Names in the bundlePreToolUse
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.
Added since
A small documentation edit on Hooks reference touched a line naming PreToolUse after this was published.
An [Agent SDK callback hook](/docs/en/agent-sdk/hooks) on `PreToolUse` that exceeds its timeout blocks the tool call, and Claude receives an error result naming the timeout.hooks see the edit
Confirmed since
Anthropic's documentation has since written up PreToolUse, on MCP, plugins, skills, and hooks.
A [`PreToolUse`](https://code.claude.com/docs/en/hooks#pretooluse) hook that runs this way and has no `onFailure` field blocks the tool call when it fails or times out. The hook error that Claude receives includes `blocking because Git Bas…third-party/claude-desktop/extensions see the edit
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubt
Whether Claude Code sends these details by default is not clear.
Anthropic's documentation agrees
Anthropic's documentation has since written up PreToolUse, on MCP, plugins, skills, and hooks.