Claude Code vs Cursor: slash commands and context syntax compared
Claude Code and Cursor's agent CLI both expose a slash-command layer on top of a chat prompt, and the two vocabularies overlap more than either vendor's marketing suggests: /clear, /model, /plan, /goal, /fork, /rewind, /rename, /resume and /logout exist in both with the same meaning. The table below pairs each task with the literal command in each tool, taken from the two reference pages on this site; a dash means the tool has no documented equivalent.
| Task | Claude Code | Cursor |
|---|---|---|
| Start a fresh conversation | /clear name | /clear |
| Shrink the context window | /compact instructions | /summarize |
| Switch model | /model model | /model [filter] |
| Enter plan mode | /plan description | /plan [prompt] |
| Set a long-lived goal | /goal condition|clear | /goal [objective] |
| Fork the session | /fork prompt | /fork |
| Rewind to an earlier point | /rewind | /rewind |
| Rename the session | /rename name | /rename <name> |
| Resume a previous session | /resume session | /resume |
| Run a shell command from the prompt | ! (at start) | /shell [command] |
| Attach a file as context | @ | @<file> |
| Ask a side question | /btw question | — |
| Read-only question mode | — | /ask |
| Attach the branch diff | — | @Branch |
| Manage MCP servers | /mcp reconnect <server>|enable|disable <server>|all | — |
| Permissions / autonomy | /permissions | /run-everything [on|off|status] |
| Show cost or usage | /usage | — |
| Fix terminal newline keybinding | /terminal-setup | /setup-terminal |
| Sign out | /logout | /logout |
The differences are mostly about surface area. Claude Code's command list is roughly four times longer because it bundles many skills as slash commands (/code-review, /security-review, /deep-research, /verify, /simplify) and exposes infrastructure switches (/mcp, /hooks, /permissions, /sandbox, /remote-control). Cursor keeps the CLI list short and moves most of that configuration into the editor. Cursor's @-mention family is richer at the prompt level, with @Branch, @Commit, @Terminals, @Chats and @Browser, where Claude Code's prompt layer has @ for file paths and ! for shell.
Two naming traps are worth knowing when switching. Context compaction is /compact in Claude Code and /summarize in Cursor; shell access is a leading ! in Claude Code but the /shell command in Cursor. Everything else either matches by name or has no counterpart, so the cost of moving between the two is small.
Full references: Claude Code (142) · Cursor (37) · all comparisons
Terminal agent versus editor agent
Claude Code runs in the terminal and treats the repository as its workspace; Cursor is an editor with the agent in a side panel and inline. The table pairs the actions that exist in both — asking about a selection, applying a multi-file change, accepting or rejecting edits, adding files as context — but the interaction model differs: Claude Code is a conversation you approve step by step, Cursor is an editor where the agent's diffs appear in place and Tab accepts them. Many people use both, Cursor for edits they will watch and Claude Code for tasks they will hand off.
Where the rows do not line up
Cursor's Tab completion and Cmd + K inline edit have no Claude Code counterpart, because there is no editor; Claude Code's hooks, CLAUDE.md project instructions and headless mode have no Cursor counterpart, because it is not a CLI. Those rows are marked rather than stretched, and the notes say which tool's page covers the feature in full.