The slash menu

Agents: claude, codex, opencode · On: phone, desktop

Type / in the composer and a list appears above it: the commands VCode runs itself, and the skills the agent can load. Tap one, walk it with the arrows, or press Tab to take the top match.

Why you would use it

You cannot remember whether the command is /effort or /reasoning, and on a phone you do not want to find out by sending it. The menu is the list, scoped to the agent this tab is running.

How to use it

1. Type / in the box (#draft). The menu (#slashmenu) opens between the transcript and the box.

   

2. Keep typing to filter. Matching is fuzzy: tdd finds test-driven-development.

   

3. Press ↓ and ↑ to walk the rows. The list wraps at both ends, and ↑ from nothing selected starts at the bottom.

   

4. Take the selected row with Enter, with Tab, or by tapping it. All three do the same thing to it. With no row selected, Tab completes the top match and Enter sends what you typed. Escape closes the menu.

5. Taking a row writes /name into the box with a trailing space, leaving the rest of your message alone — unless the command runs on its own, and then it runs where you took it. /clear clears, /new opens a tab in this folder, /resume opens the session list, /exit closes the tab.

6. A command you typed out in full runs on Tab as well: /clear and one press, with nothing left to complete. /cl and one press is still /clear.

What you see

• A header line: the agent, then the count, then what Tab will do — claude · 12 matches · ⇥ /clear. Once the arrows have moved, the hint names the row they are on.
• The selected row lights its border and background, the way the folder box marks the folder you are in.
• In a list of values, the model or effort the tab is already on carries a green tick and reads in use at the head of its note. Every agent row carries its brand mark, so that menu says which one is running with brighter text and the note running this tab now.
• With more matches than fit, the header says so: 46 matches · showing 40, keep typing.
• Each row is the command or skill name with the characters that earned the match highlighted, then its description. A skill with no description reads skill.
• A row for /clear, /new, /resume or /exit acts on the pick: the menu closes and the command runs, with nothing left in the box to send. The others take an argument, so taking them writes the name and waits — /model and /effort then open their list of values, /handoff and its aliases their list of agents.
• /new is the one that both runs and takes an argument. Taken from the menu it opens a tab in this tab's folder; type a space after it and the folder list opens instead.
• A finished /model or /effort turns the menu into that command's values, headed model for claude · now: sonnet, with no space needed: VCode owns both words on every agent, so the word on its own is already the question. A finished /handoff, /vendor, /harness or /agent turns it into the agent list instead, headed agent for this tab · now: claude. /new waits for the space before it lists folders.
• Both work at the end of a message already written, not only on an empty box: type write the tests /model and the models are listed. Picking one sets it and takes the command out of the draft, leaving write the tests to send. /new is the exception — it stays a command on its own, because its menu writes a folder path back into the box.
• The command the caret is in is the one answered, so a second command later in the draft gets its own menu: in fix the bug /model opus then /compact the menu is the command list for /compact. Move the caret out and the menu closes.
• A menu opened by tapping the agent, model or effort button leaves a message in the box alone. Only a command you typed is taken out of it — and a box holding nothing but /model is emptied either way, since picking spends it.
• On a desktop frame the menu opens over the transcript, above the pane's attachments, subagents strip and status line. Nothing moves: the transcript stays where it was and shows either side of the menu, and the rows under the menu stay against the composer.

Options and settings

VCode's own commands, from public/commands.js. Each is listed only for the agents that have it; all ten are listed for all three agents today.

A command with a dash under Takes runs on the pick, and so does /new, whose folder is optional; the rest are written into the box for you to finish.

/compact is also listed, for claude and opencode, as a pass-through: the menu offers it, and the text is sent to the CLI exactly as typed.

Limits and known gaps

• The list is capped at 40 rows. The header reports the true total and admits the cap.
• The menu is Agent mode only. In Shell mode /usr is a path, so no menu opens.
• A slash glued to the end of a word, or with a space or a second slash between it and the caret, is prose or a path, not a command.
• Enter sends until an arrow has chosen a row, so a command typed in full is still one keypress. After a move it takes the row instead.
• Tab runs a command only when there is nothing left to complete: a row the arrows chose, or the whole box already holding that command. /cl plus one press is /clear, not a cleared conversation.
• A skill is never run from the menu, by any of the three keys: skills resolve inside the agent, so the row writes its name and the message is sent. The same goes for /compact, which the CLI answers itself.
• A command picked out of the middle of a longer message is written in as text even when it takes no argument. Running it there would empty the box and take the message with it.
• Any keystroke that changes the list drops the selection, because the row it was on may not be in the new list.
• The arrows belong to the menu while it is open, so they neither move the caret in a multi-line draft nor walk the prompt history. Escape gives them back.
• A menu opened by tapping the agent, model or effort button takes the arrows only once the focus is back in the composer, which a tap in the box does: the keys are listened for there, and the tap on the button moved the focus to the button.
• Skills are read from ~/.claude/skills and ~/.codex/skills, three levels deep. opencode has no skills directory, so an opencode tab's menu is commands only.
• A vendor built-in VCode cannot run is not in the menu; typing it gets an explanation instead. See vendor-slash-commands.

Related

• navigation-and-commands — every gesture, key and command, phone and desktop
• vendor-slash-commands — what the CLI's own commands do when typed here
• clear-the-context, switch-the-model, set-the-effort
• agent-or-shell-mode — the mode the menu needs
• type-to-start-a-message — typing / with the focus nowhere opens it too
• new-tab-command — what /new opens
• resume-a-session-from-disk — what /resume lists
• auto-compact — what /autocompact sets
• clear-the-message-box — the second Escape, once the menu is closed