Follow Discord
Sweep 27 Oct 2026 · 19:04Z Build v2.1.312 531 read Stable v2.1.308 Latest v2.1.312 Next v2.1.312 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.312 ·

Claude Code can now say who a skill comes from

Claude Code can label a skill as built in, from your organization, or shared with you, when a remote switch allows it

Under the hood Internal Changes
JSON All of v2.1.312
Under the hoodTier: how much it should matter to you
2Useful: my rating, 1 to 5
3Signal: worth watching, 1 to 5
SkillsArea: what it touches
Internal ChangesKind: in v2.1.312,
Internal ChangesSection of the release
What

A skill is a packaged set of instructions Claude can use for a particular kind of task. Claude Code can now describe where a skill comes from with one of three labels:

  • "built in"
  • "one of the organization's skills"
  • "a skill shared with the user"

If a skill's origin is unknown, no label is given. The labels are produced only when a switch controlled from Anthropic's side is turned on.

Why

The labels give Claude Code a way to tell you whose skill is about to run. That matters most when a skill came from someone other than you.

Read from
Feature flag
tengu_reflective_donut 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: no value returned · compiled default in v2.1.312: off

These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.

Read once, for one account on one subscription tier, against v2.1.312. It isn't a statement about your account. What a flag value here can and cannot tell you

How sure we are
One source agreesOne thing we can check says the same as this entry.
The name it cites is new in this buildNew in this build: tengu_reflective_donut

See this entry in the whole of v2.1.312 →

Feedback