Follow Discord
Sweep 06 Nov 2026 · 01:32Z Build v2.1.319 537 read Stable v2.1.311 Latest v2.1.318 Next v2.1.319 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.257 ·

Hooks declared outside the "hooks" key (or PreToolUse/PermissionRequest nested arrays) now fail to load with a clear error

A plugin or agent declaring PreToolUse or PermissionRequest hooks in the wrong place is now rejected with a clear error.

You'll notice Bug Fixes
JSON All of v2.1.257
You'll noticeTier: how much it should matter to you
2Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
HooksArea: what it touches
Bug FixesKind: in v2.1.257,
Bug FixesSection of the release

Plugin manifests, marketplace entries, and agent frontmatter that declare PreToolUse/PermissionRequest hooks at the top level, under an unrecognized key, or nested in arrays this build cannot parse, now cause the plugin or agent to be rejected as "unloadable" with an explicit message, instead of failing validation silently elsewhere.

Read from
Names in the bundlePreToolUsePermissionRequest
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.

Added since A small documentation edit on Choose a permission mode touched a line naming PreToolUse after this was published. If you set `dontAsk` mode, Claude Code auto-denies every tool call that would otherwise prompt you. Claude still runs actions that need no approval in Manual mode, such as file reads inside your working directories and [read-only Bash comm… permission-modes see the edit
Confirmed since Anthropic's documentation has since written up PermissionRequest, on Claude Code changelog. * Fixed PermissionRequest hooks not firing in `--print` mode changelog see the edit
Confirmed since Anthropic's documentation has since written up PreToolUse, on migration. | `PreToolUse` / `PostToolUse` hooks | Your client already sees every `agent.custom_tool_use` event before responding; put the logic there. For built-in tools, use `permission_policy: always_ask` to review every call. [`auto`](https://plat… managed-agents/migration see the edit
How sure we are
One source agreesOne thing we can check says the same as this entry.
Anthropic's documentation agreesAnthropic's documentation has since written up PreToolUse, on migration.

See this entry in the whole of v2.1.257 →

Feedback