Slash commands can mark themselves terminal-only, and SDK…

What

Commands that only make sense in the CLI, such as /doctor, /exit, /statusline and /reload-plugins, are now flagged as terminal-oriented. The startup system/init message sent to SDK clients carries a new terminal_slash_commands array naming those commands, so a non-terminal host can hide or reject them instead of offering commands it cannot run. The array is left out entirely when nothing is flagged.

Details

Command definitions gained a terminalOriented field; only user-invocable commands appear in the array.

Evidence

terminal_slash_commands

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Read from

Names in the bundle/doctor/exit/statusline/reload-pluginsterminal_slash_commands

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.

Confirmed since 10 Sep 2026 Anthropic's documentation has since written up /doctor, on CLI reference. | `claude doctor` | Print read-only installation and settings diagnostics from the terminal without starting a session, including install health, settings-file validation errors, and Remote Control eligibility. For the in-session setup che… cli-reference see the edit

Added since 10 Sep 2026 A small documentation edit on Push events into a running session with channels touched a line naming /reload-plugins after this was published. When the install asks for an installation scope, choose the user scope option so the plugin is available across all your projects. Check the install summary: if it reports `Run /reload-plugins to activate.`, see [Apply plugin changes witho… channels see the edit

Added since 10 Sep 2026 A small documentation edit on Recommend your plugin from your CLI touched a line naming /statusline after this was published. * `CLAUDE_CODE_CHILD_SESSION`: set only in subprocesses Claude Code itself spawns, such as tool calls, hook commands, and [status line](/docs/en/statusline) commands, so the tag does not normally reach a human terminal. A long-lived proces… plugin-hints see the edit

Confirmed since 10 Sep 2026 Anthropic's documentation has since written up /reload-plugins, on Claude Code changelog. * Improved `/plugin`: installing, enabling or disabling a plugin now takes effect when you close the menu; `/reload-plugins` is no longer needed afterwards changelog 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 /reload-plugins, on Claude Code changelog.

Anthropic's release notes agreeImproved sandbox: IPv6 literals in network domain lists are now bracketed ([::1]:443), and ambiguous spellings are enforced fail-closed and…

See this entry in the whole of v2.1.229 →

The build it came inv2.1.229

12 Aug 2026 · 205 entries, this one is #62.

Use it now23
You'll notice87
Nothing to try yet28
Under the hood67

Either side of it

v2.1.228Older
v2.1.231Newer

Open the release →

Names in this entry

slash/doctor
Skill. Run a setup checkup that diagnoses issues and can fix them. Checks installation health, including duplicate or leftover installs, PATH problems, and unparseable settings files. Finds unused skills, MCP servers, and plugins versus their context cost, flags slow hooks, and checks for a newer version on your release channel. Deduplicates local CLAUDE.md files against checked-in ones, trims checked-in CLAUDE.md files by cutting content Claude could derive from the codebase, and migrates the always-loaded guidance that remains into skills and nested CLAUDE.md files that load on demand. Also offers to make auto mode your default and to pre-approve frequently denied read-only commands. Reports findings first and asks for confirmation before changing anything. From the terminal, claude doctor prints read-only installation diagnostics without starting a session. Alias: /checkup. Run /doctor prompt-audit to have Claude audit your CLAUDE.md files, skills, and other configuration for outdated or conflicting instructions instead of running the checkup. The prompt-audit subcommand requires Claude Code v2.1.283 or later. The CLAUDE.md trim check requires Claude Code v2.1.206 or later. Before v2.1.205, /doctor opened a read-only diagnostics screen and pressing f sent the report to Claude
slash/exit
Exit the CLI. In an attached background session, this detaches and the session keeps running. Alias: /quit
slash/statusline
Configure Claude Code's status line. Describe what you want, or run without arguments to auto-configure from your shell prompt
slash/reload-plugins
Reload all active plugins to apply pending changes without restarting. Reports counts for each reloaded component and flags any load errors. When the reload would change which MCP tools are loaded and invalidate the prompt cache, the command warns and skips unless you pass --force. Also available in non-interactive mode (-p), the Agent SDK, and the desktop app, where it runs only on input typed directly into the session and doesn't apply plugin MCP server changes; requires Claude Code v2.1.260 or later. See Apply plugin changes without restarting
settingsystem
SDK callers get an mcp_server_errors array naming rejected MCP configs, so CI can fail on it.

Anthropic's note

Upstream's own release notes for v2.1.229 name something this entry names, so the two are probably about the same change. Probably: the pairing is made on a shared name rather than on the words around it.

Improved sandbox: IPv6 literals in network domain lists are now bracketed ([::1]:443), and ambiguous spellings are enforced fail-closed and flagged by /doctor

Is this right?

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

v2.1.260 New cloud-terminal restriction message for /statusline
Both mention statusline