Follow Discord
Sweep 22 Oct 2026 · 04:32Z Build v2.1.308 527 read Stable v2.1.308 Latest v2.1.308 Next v2.1.308 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.305 ·

Claude in Chrome instructions are restructured and tool search knows a batch tool

The long Claude in Chrome guidance on GIFs, console logs, alerts and tabs is gone from its old place, and tool search now mentions a batch browser tool

Nothing to try yet In Development
JSON All of v2.1.305
Nothing to try yetTier: how much it should matter to you
2Useful: my rating, 1 to 5
3Signal: worth watching, 1 to 5
Chrome & BrowserArea: what it touches
In DevelopmentKind: in v2.1.305,
In DevelopmentSection of the release
What

Claude in Chrome lets Claude control your Chrome browser. The instructions Claude Code gives the model for it have been restructured. Long sections on recording GIFs, reading console logs, handling alerts, avoiding rabbit holes and tab context are no longer in the same place. A new step can rewrite this text, but only when a setting controlled by the server is switched on.

The hint for tool search, which loads tools only when needed, now also lists a browser_batch tool.

Why

This may change the browser guidance the model works from.

Read from
Feature flag
tengu_tranquil_starlight 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 v2.1.305: 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 v2.1.305. It isn't a statement about your account. What a flag value here can and cannot tell you

What has happened since
Flag reading moved The flag server now returns off for tengu_tranquil_starlight, 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.
Flag reading moved The flag server now returns nothing at all, having stopped carrying it for tengu_tranquil_starlight, 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
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_tranquil_starlight

See this entry in the whole of v2.1.305 →

Feedback