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 v2.1.235 ·

New opt-in prompt-input spell checking (aspell/hunspell/ispell)

Claude Code can now spell-check prompt input using aspell, hunspell, or ispell if you opt in

Use it now Notable New Features
JSON All of v2.1.235
Use it nowTier: how much it should matter to you
5Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
Spell CheckArea: what it touches
New FeaturesKind: in v2.1.235,
What probably matters to youSection of the release

A new spellcheck settings block adds spell checking to the prompt input, underlining misspelled words. It ships off by default; the schema's default is enabled: false, and turning it on shells out to whichever of aspell, hunspell, or ispell it finds on PATH (or a specific one via the checker sub-key, default auto), parsing the tool's ispell-protocol output. Other sub-keys are language (a plain dictionary name) and color. The block is only honored from user, flag, or managed settings; a spellcheck block in project .claude/settings.json or .claude/settings.local.json is ignored with a warning. If no supported checker is installed, spell checking silently stays off. Usage is reported via input_spellcheck telemetry.

Read from
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 Continue local sessions from any device with Remote Control touched a line naming language after this was published. If you didn't set an explicit name, Claude Code updates the title to reflect your prompt once you send one. Claude Code matches auto-generated titles to the language of your conversation, or to the [`language`](/docs/en/settings-reference#… remote-control see the edit
Added since A small documentation edit on Specification Enhancement Proposals (SEPs) touched a line naming color after this was published. | [SEP-2640](/seps/2640-skills-extension) | Skills Extension | <Badge color="green" shape="pill">Final</Badge> | Extensions Track | 2026-04-23 | seps/index see the edit
Confirmed since Anthropic's documentation has since written up color, on Claude Code changelog. * Fixed stray characters like `22c`, or a terminal's color or version reply, being typed into the prompt at startup over slow connections (ssh, browser terminals) changelog see the edit
Added since A small documentation edit on Interactive mode touched a line naming enabled after this was published. Unless your session is one of those listed under [strict sandbox mode](/docs/en/sandboxing#the-unsandboxed-retry-escape-hatch), commands you type in shell mode run outside the [sandbox](/docs/en/sandboxing) even when you've enabled sandbox… interactive-mode see the edit
Confirmed since Anthropic's documentation has since written up checker, on Claude Code changelog. * Fixed a case where a Read or Edit deny rule did not apply when an `env -C`, `eval` or similar command the permission checker cannot analyze was on the same line changelog see the edit
Confirmed since Anthropic's documentation has since written up language, on permission-policies. <MultiFileExample language="cli" label="CLI"> managed-agents/permission-policies see the edit
How sure we are
Two sources agreeTwo things we can check say the same as this entry.
Anthropic's documentation agreesAnthropic's documentation has since written up enabled, on MCP, plugins, skills, and hooks.
The name it cites is new in this buildNew in this build: checker

See this entry in the whole of v2.1.235 →

Feedback