Follow Discord
Sweep 22 Oct 2026 · 21:04Z Build v2.1.309 528 read Stable v2.1.308 Latest v2.1.309 Next v2.1.309 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.229 ·

Plugins can be installed from a command that prints a directory

Marketplaces can install a plugin by running a command that prints a directory path, with your consent.

Use it now Notable New Features
JSON All of v2.1.229
Use it nowTier: how much it should matter to you
3Useful: my rating, 1 to 5
3Signal: worth watching, 1 to 5
PluginsArea: what it touches
New FeaturesKind: in v2.1.229,
What probably matters to youSection of the release
What

Plugin sources now include command: a shell command that prints the absolute path of a plugin directory. It is re-resolved on install, on update and once per session in the background, takes an optional timeout, and a mode of copy or link decides whether the directory is copied into the plugin cache or used in place. Installing one asks for consent first.

Details
  • The command string must be printable ASCII and short enough for the consent prompt to display in full, so it can be read before you approve it.
  • Declining the consent prompt is recorded as command_source_declined.
  • link mode serves the plugin from the producer's directory rather than a cache copy.
Evidence

command must be printable ASCII (letters, digits, punctuation, single spaces) with no runs of 4 or more spaces

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Read from
Names in the bundlecommandtimeoutmodelinkcopy
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 How Claude remembers your project touched a line naming link after this was published. The `.claude/rules/` directory supports symlinks, so you can maintain a shared set of rules and link them into multiple projects. Circular symlinks are detected and handled gracefully. memory see the edit
Confirmed since Anthropic's documentation has since written up timeout, on Batches. - `type: "timeout_error"` api/messages/batches see the edit
Added since A small documentation edit on Custom connectors touched a line naming command after this was published. Local-command connectors run inside the sandbox with the same network limits as Claude's code and a per-connector writable directory. Environment variables for local connectors are saved unencrypted in a configuration file readable by your… claude-science/custom-connectors see the edit
Confirmed since Anthropic's documentation has since written up copy, on Use Claude Science on a corporate network. Claude Science stores the credential encrypted in its local database, using a key kept in a file only the member's account can read (on macOS, a copy of that key is in the keychain for recovery), and also writes the credential, automatical… claude-science/corporate-networks see the edit
Confirmed since Anthropic's documentation has since written up mode, on Model configuration. * The model doesn't support `xhigh` effort model-config see the edit
Added since A small documentation edit on User identity and local data touched a line naming copy after this was published. | `vm_bundles/` | Cached copy of the VM workspace bundle that Cowork sessions run in, plus the data disk the app creates to hold those sessions' home directories inside the VM. | third-party/claude-desktop/data-storage 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 command, on MCP, plugins, skills, and hooks.

See this entry in the whole of v2.1.229 →

Feedback