Unclear What the new prompt_line choice for reveal does is not clear.
What
The prompt box has more than one input mode. Bash mode treats what you type as a shell command; prompt mode treats it as a message or slash command. Several commands that Claude Code submits for you now say which mode to use:
- When the usage limit menu opens on its own,
/rate-limit-optionsis now submitted withinputModeOverride: "prompt", so it is not treated as bash input. Before, it was submitted with no override. - The
/artifactskeyboard shortcut now also submits in prompt mode. - The
/clearkeyboard shortcut no longer forces prompt mode itself; the override is applied on a different path. It now passesleavesIdeSelection, and a keyboard shortcut path for/artifactspasses it too. - After submitting, Claude Code now resets the input mode unless the override came from a keyboard shortcut or asked to keep the composer (
keepsComposer).
In the same area, a settings reveal option now accepts prompt_line as well as login_handoff and default.
Why
If you were in bash mode when the usage limit menu opened automatically, it could be treated as a shell command and fail. These commands now open as intended whatever mode you were in.
Names in the bundle/artifacts
/artifacts
Configure cloud environments modified, high confidence
If your organization uses [artifacts](/docs/en/artifacts.md#availability), you don't need `*.frame.claudeusercontent.com` in the list for sessions to read them. When the list leaves that host out, Claude Code reads artifact content through…see the edit
/artifacts
Desktop application modified, high confidence
An [artifact](/docs/en/artifacts.md) that loads a typeface from [Google Fonts](/docs/en/artifacts.md#improve-the-visual-design) also requests `fonts.googleapis.com` and `fonts.gstatic.com`. Both hosts are optional. If you block them, artif…see the edit
/artifacts
Connect Claude Code to tools via MCP modified, high confidence
Anthropic also provides some connectors itself, without you or an admin adding them. On accounts where [Claude Docs](/docs/en/artifacts.md#write-a-document-with-claude-docs) is available, `/mcp` lists `claude.ai Claude Docs` with no setup,…see the edit
/artifacts
Enterprise network configuration modified, high confidence
| `*.frame.claudeusercontent.com` | [Artifact](/docs/en/artifacts.md) content reads. The CLI fetches an artifact's files from this host when Claude opens one, and only when the Artifact tool is [available](/docs/en/artifacts.md#availabilit…see the edit
/artifacts
Choose a permission mode modified, high confidence
> * When Claude reads an [artifact someone else made](/docs/en/artifacts.md#read-an-artifact-shared-with-you), the approval cases listed in that section applysee the edit
/artifacts
Configure permissions modified, high confidence
The two forms also differ on reads of [artifacts](/docs/en/artifacts.md), the pages the Artifact tool publishes on claude.ai. A bare `WebFetch` deny or ask rule doesn't apply to those reads. A `domain:` rule covering `claude.ai` or the `*.…see the edit
/artifacts
Automate work with scheduled tasks modified, high confidence
When a scheduled task's schedule or **Run now** starts a run, Claude can publish a new [artifact](/docs/en/artifacts.md) without asking. The new artifact is visible only to you until you [share it](/docs/en/artifacts.md#share-an-artifact).…see the edit
/artifacts
Deploy self-hosted environments to production modified, high confidence
| `*.frame.claudeusercontent.com` | 443 | Only when the [Artifact tool](/docs/en/artifacts.md#availability) is available for sessions in your organization; defaults vary by plan, per the availability table there. Set `CLAUDE_CODE_DISABLE_A…see the edit
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.
Confirmed since
Anthropic's documentation has since written up /artifacts, on Manage multiple agents with agent view.
* **Carries over**: running background shell commands, backgrounded subagents, scheduled tasks you created with [`/loop`](https://code.claude.com/docs/en/scheduled-tasks), and Claude's [automatic replies to artifact comments](https://code.…agent-view see the edit
Added since
A small documentation edit on Connect Claude Code to tools via MCP touched a line naming /artifacts after this was published.
Anthropic also provides some connectors itself, without you or an admin adding them. On accounts where [Claude Docs](https://code.claude.com/docs/en/artifacts.md#write-a-document-with-claude-docs) is available, `/mcp` lists `claude.ai Clau…mcp see the edit
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubt
What the new `prompt_line` choice for `reveal` does is not clear.
Anthropic's documentation agrees
/artifacts on Configure cloud environments