What are slash commands?
Slash commands are controls typed with a leading / in the prompt of a coding agent: built-ins such as /clear, /compact, /model, /plan and /review, and your own commands, written as skills in Claude Code or kept in .cursor/commands/ in Cursor. Type / in Claude Code or Codex and the live list for your build appears; it is the only inventory that stays correct.
- In Polish
- Komendy slash
- First set up at
- Level 2, free guide
- Also searched as
- /commands, custom commands
$59.99 once for 12 months of access. Nothing renews on its own. 30-day refund on a first purchase.
Why it matters.
In Claude Code a custom command is a committed file, so every teammate gets the same /NAME workflow and one engineer’s pre-PR routine stops being the only one that catches the missing test. The built-ins carry the opposite risk, a list that ages: a command counts only at the start of a message, and Anthropic’s own reference listed 114 entries on 2026-09-26, so type / instead of trusting a blog post.
How each tool does it.
Cursor, Claude Code and Codex each name this their own way. Each note carries the date it was checked.
Cursor
The Cursor CLI lists /goal (marked “Rolling out” in Cursor’s docs, checked 2026-10-12), /rewind and /sandbox among its slash commands; the full set was not re-verified. Custom commands live in .cursor/commands/, which many repositories still use.
The Cursor docs prefer skills for new workflows, because the SKILL.md format is shared with Claude Code and Codex, although each tool reads its own directory (team collaboration guide).
Feature matrix (Cursor docs), 2026-08-28
Claude Code
Built-ins such as /clear, /compact, /model, /effort, /plan and /code-review (alias /review), plus your own: a skill at .claude/skills/NAME/SKILL.md creates /NAME.
Custom commands have merged into skills: older .claude/commands/NAME.md files still work, but a skill folder is preferred for new work because it can hold scripts and reference files. allowed-tools pre-approves tools for that turn; it does not restrict them.
Command reference, Claude Code 2.1.283, 2026-09-26
Codex
Type / in the composer for the list: /review, /diff, /status, /model, /plan, /goal, /init and more. There is no /help.
/skills lists the skills Codex loaded. Most commands, /compact, /new, /init, /review and /plan among them, are unavailable while a turn is running: press Esc first.
Codex CLI commands guide, Codex 0.157.1, 2026-10-03
Questions about slash commands.
Is there a /think command in Claude Code?
No. think, think hard and think more are ordinary prompt text. ultrathink asks for deeper reasoning on one turn without changing the effort sent to the API; lasting depth is set with /effort or claude --effort. Plan mode is entered with Shift+Tab or /plan.
How do I see which commands exist?
Type / and filter. Claude Code and Codex both show the list for your build, and it is the only inventory that stays correct: Claude Code’s reference listed 114 entries on 2026-09-26, and the set changes between releases. Codex has no /help.
Can I write my own slash commands?
In Claude Code, yes: a skill at .claude/skills/NAME/SKILL.md creates /NAME, and older .claude/commands/NAME.md files still work. Codex exposes the same idea through skills, listed by /skills. Cursor keeps custom slash commands in .cursor/commands/, which many repositories still use, and its docs prefer skills for new workflows (team collaboration guide, 2026-09-26); the CLI also lists /goal, /rewind and /sandbox (docs read on 2026-08-28).
Why does /review ignore my custom command?
In Claude Code /review is the alias of the bundled /code-review, and aliases never run your skill. A project skill named code-review replaces /code-review but not /review. Name your command /team-review or /pre-pr so nobody has to guess which one ran.
Keep reading.
The guides that go deeper, and the terms and comparisons next to this one.
In the docs
Does this page answer your questions?
One tap, no sign-in.
What are you here for?
What is holding you back?
How does it read?
Thanks. If you left an email, Michał will reply.
Answering your questions?
One tap each. Close whenever you like.
no sign-in
Read the guides in the same words.
Open every guide with the Toolkit. Each term is defined once here, and the guides use it the same way.
$59.99 once for 12 months of access. Nothing renews on its own. 30-day refund on a first purchase.
Michał replies, not a bot. The address is used for this reply only.