claudekit / guides / hidden-commands
[ Guide · Practical · 7 min ]

Hidden Claude Code commands you actually want to use

updated

Built-in slash commands that get buried even though they only need a single line to run — /radio, /btw, /teleport, /context, /copy, /loop and more, organized by when you'd reach for them.

Why this guide

Most people skim /help once and end up reaching for the same five or six commands every day. There’s a long tail of built-ins that quietly stay buried even though they need no setup and a single line to run. A handful of them change how a daily session feels.

When you need a quick break

  • /radio

    Opens Claude FM lo-fi radio in your browser. Prints the stream URL when no browser is available. Not available on Bedrock, Vertex, or Foundry.

    Claude FM lo-fi radio player opened by the /radio command in a Claude Code session

  • /btw <question>

    Ask a quick side question without adding to the conversation history. Useful when you want to confirm something without polluting context.

  • /color [color|default]

    Set the prompt bar color (red, blue, green, yellow, purple, orange, pink, cyan, or default). Helpful for telling parallel sessions apart at a glance.

Move sessions freely

  • /teleport (alias /tp)

    Pull a Claude Code on the web session into your current terminal — opens a picker, then fetches the branch and conversation. Requires a claude.ai subscription.

  • /remote-control (alias /rc)

    The inverse: make your local session controllable from claude.ai. Useful for checking in or directing work from a phone.

  • /branch [name] (alias /fork)

    Create a branch of the current conversation at this point. Switches you into the branch and preserves the original, which you can return to with /resume.

  • /clear [name] (aliases /reset, /new)

    Start a new conversation with empty context. Pass a name and the previous conversation shows up labeled in the /resume picker.

When context feels heavy

  • /context [all]

    Visualize current context usage as a colored grid. Shows what’s eating your window — memory, tool calls, files — alongside optimization suggestions. Pass all to expand the per-item breakdown.

  • /compact [instructions]

    Free up context by summarizing the conversation so far. Pass focus instructions to steer how the summary is shaped.

Get results out

  • /copy [N]

    Copy the last assistant response (or the Nth-latest with /copy 2) to clipboard. When code blocks are present, opens an interactive picker to select individual blocks or the full response. Press w in the picker to write the selection to a file instead — useful over SSH.

  • /export [filename]

    Export the current conversation as plain text. With a filename, writes directly to that file; without, opens a dialog to copy to clipboard or save to a file.

  • /diff

    Open an interactive diff viewer that shows uncommitted changes and per-turn diffs. Use left/right arrows to switch between the current git diff and individual Claude turns; up/down to browse files. Great for a final pass before opening a PR.

Review workflows

  • /simplify [focus]

    Bundled skill. Reviews recently changed files for code reuse, quality, and efficiency, then applies fixes. Spawns three review agents in parallel and aggregates the findings. Pass focus text — for example /simplify focus on memory efficiency.

  • /review [PR]

    Review a pull request locally in your current session. For a deeper cloud-based review, see /ultrareview.

  • /security-review

    Analyze pending changes on the current branch for security vulnerabilities. Reviews the git diff and identifies risks like injection, auth issues, and data exposure.

Automate sessions

  • /loop [interval] [prompt]

    Bundled skill. Run a prompt repeatedly while the session stays open. Omit the interval and Claude self-paces between iterations. Example: /loop 5m check if the deploy finished.

  • /effort [level|auto]

    Set the model effort level immediately (low, medium, high, xhigh, max). With no argument, opens an interactive slider — left/right arrows to pick, Enter to apply.

  • /plan [description]

    Enter plan mode directly from the prompt. Pass an optional description to enter plan mode and immediately start with that task — for example /plan fix the auth bug.

Wrap up

Type / inside a Claude Code session to see the full menu. The list looks intimidating, but you really only end up using five to ten of them regularly — slip two or three of these into your habit and the daily flow gets noticeably lighter.

§ 9

Frequently Asked Questions

frequently asked
§ 9.1
Who is this guide for?
Anyone who has been using Claude Code for a while and ran `/help` once, but realizes they keep reaching for the same five or six commands. These are built-ins that need no installation — just a single line.
§ 9.2
Where do I see the full command list?
Type `/` inside a Claude Code session to open the autocomplete menu with every available command. `/help` surfaces the same information.
§ 9.3
Where doesn't /radio work?
It is not available on Amazon Bedrock, Google Vertex, or Microsoft Foundry. It works on direct Anthropic API connections.
§ 9.4
What's the difference between /teleport and /remote-control?
`/teleport` pulls a Claude Code on the web session into your terminal (web → local). `/remote-control` does the inverse: makes your local session controllable from claude.ai (local → web).
§ 9.5
What's the difference between /branch and /clear?
`/branch` creates a fork of the current conversation at this point and switches you into the branch — the original is preserved and reachable through `/resume`. `/clear` starts a brand-new conversation with empty context, with the previous one available in the `/resume` picker.