Follow Discord
Sweep 22 Sep 2026 · 17:19Z Build v2.1.280 501 read Stable v2.1.267 Latest v2.1.280 Next v2.1.280 Feeds RSS JSON llms.txt Unofficial
Claude Code v2.1.265 ·

Artifact tool actions consolidated into list/read with a scope

← All of v2.1.265 Home All releases

Artifact tool messages now describe actions as unified "list"/"read" with a scope or path instead of separate per-type action names

TierNothing to try yethow much it should matter to you
Useful3my rating, 1 to 5
Signal3worth watching, 1 to 5
AreaArtifactswhat it touches
KindIn Developmentin v2.1.265,
Group of 2 Nothing to try yet

Artifact tool messages now describe actions as unified "list"/"read" with a scope or path instead of separate per-type action names

What

When the consolidated "artifact toolset" is active, tool-result and instruction text for artifact tools is rewritten to use unified action names:

  • Old action names like action "list_assets", action "read_file", and action "list_files" (used by asset_upload, asset_list, asset_delete, file_list, and file_read) now appear as action "list" or action "read", with a scope (for example scope: "assets" or scope: "files") or a path argument instead.
  • Guidance that used to say action: "describe_type" now says action: "read" when this consolidated toolset is active.

Why

Collapsing several type-specific action names into a common list/read pair with a scope or path makes the artifact tool's interface simpler and more consistent for anything that reads or lists artifact content.

Read from
Feature flag
tengu_cobalt_plinth_damson Not enough to say

Nothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.

This account: no value returned · anonymous baseline: off · compiled default in v2.1.265: off

Read once, for one account on one subscription tier, against v2.1.265. It isn't a statement about your account. What a flag value here can and cannot tell you

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 Customize Claude Tag touched a line naming scope after this was published. The Configure page also shows the channel's resolved access. Its **Tools and access** tab lists the channel's resolved connections and any allowed domains. Members can see those lists but not change them there. The same tab's **Plugins** c… claude-tag/admins/customize see the edit
Confirmed since Anthropic's documentation has since written up scope, on Give Claude access to your tools. A connection grants access; a plugin teaches Claude how to use it well. A plugin is a packaged set of skills: reusable instructions for working with a specific tool or following a specific process. Attach a plugin to the same Access bundle… claude-tag/admins/add-connections see the edit
What has happened since
Flag reading moved The flag server now returns on for tengu_cobalt_plinth_damson, read as this account. A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.

See this across every release →

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 doubtThe gate `tengu_cobalt_plinth_damson` behind this change last read off for this site's account and off for the anonymous baseline, with no…
Anthropic's documentation agreesAnthropic's documentation has since written up scope, on Give Claude access to your tools.

See this entry in the whole of v2.1.265 →

Feedback