All vikis
007 First Light
AI
Aion 2
Ananta
ARC Raiders
ArcheAge Chronicles
Call of Duty: Modern Warfare 4
ChatGPT
Chrono Odyssey
Civilization 3
Civilization 4
Crimson Desert
Deadlock
Diablo 4
Diablo 5
Enshrouded
Fable
Final Fantasy Resonance
Football Manager 27
Forza Horizon 6
God of War
Grand Theft Auto 6
Heroes of Might and Magic 3Claude Code Slash Commands
Claude Code's slash commands are typed at the start of a message, such as /clear, /compact, /model, /init, /rewind and /usage. Anthropic's list had 121 entries on Nov 6, 2026, counting bundled skills and workflows, and your own commands are skills in .claude/skills/ or .claude/commands/.
Slash commands control Claude Code from the prompt: type / at the start of a message to see them, for example /clear for a fresh conversation, /compact to summarize it, /model to switch models, /init to write a CLAUDE.md and /rewind to undo (Commands). Anthropic's command reference listed 121 entries on Nov 6, 2026, mixing built-in commands with bundled skills (such as /code-review) and bundled workflows (/deep-research); which ones appear depends on your platform, plan and environment. A command only counts at the very start of a message. Commands sent while Claude is working wait their turn, except a few such as /status, /tasks and /usage, which run at once. Your own commands are Skills: a Markdown file in .claude/skills/<name>/SKILL.md or .claude/commands/<name>.md becomes /<name>.
Quick facts
| How to see them | Type / (or /help) |
| Entries in the reference | 121, including bundled skills and workflows (as of Nov 6, 2026) |
| Most used | /clear, /compact, /model, /init, /rewind, /usage, /resume |
| Your own commands | .claude/skills/<name>/SKILL.md or .claude/commands/<name>.md |
| Personal commands | ~/.claude/skills/<name>/SKILL.md |
| Arguments | $ARGUMENTS, or $0, $1 by position |
| Removed | /vim (2.1.92), /pr-comments (2.1.91), /ultraplan |
Source: Commands, Extend Claude with skills, read Nov 6, 2026.
Conversation and context
| Command | What it does |
|---|---|
/clear [name] |
Starts a new conversation with empty context |
/compact [instructions] |
Summarizes the conversation so far to free context |
/context |
Shows context use as a colored grid |
/autocompact |
Sets how full context gets before automatic compaction |
/rewind |
Rewinds conversation and code to an earlier prompt (Claude Code Checkpoints) |
/resume [session] |
Reopens a past conversation, or a picker |
/branch [name] |
Branches the conversation to try another direction |
/fork [prompt] |
Copies the conversation into a new background session |
/rename [name] |
Names the session |
/btw [question] |
Asks a side question that stays out of the conversation |
/recap |
Summarizes the session in one line |
/export [filename] |
Saves the conversation as plain text |
/copy [N] |
Copies the last reply to the clipboard |
/diff |
Shows the changes in the working tree, Claude's included |
/add-dir <path> |
Gives the session access to another folder |
/cd <path> |
Moves the session to another folder |
/exit (/quit) |
Exits |
Models and effort
| Command | What it does |
|---|---|
/model [model] |
Switches model and saves it as the default |
/effort [level] |
Sets effort from low to max, or turns ultracode on |
/fast [on|off] |
Toggles fast mode |
/advisor [model|off] |
Lets Claude consult a second model at key moments |
/goal [condition] |
Keeps Claude working across turns until a condition is met |
/plan [description] |
Enters plan mode |
Project setup and customization
| Command | What it does |
|---|---|
/init |
Writes a starter CLAUDE.md for the project (CLAUDE.md and Memory) |
/memory |
Edits CLAUDE.md files and manages auto memory |
/config |
Opens settings: theme, model, editor mode and more |
/permissions |
Manages allow, ask and deny rules (Claude Code Permissions and Modes) |
/hooks |
Shows hook configuration (Claude Code Hooks) |
/agents |
Points to creating and managing subagents (Claude Code Subagents) |
/skills, /reload-skills |
Lists skills; rescans them from disk |
/plugin, /reload-plugins |
Manages and reloads plugins (Claude Code Plugins) |
/mcp |
Manages MCP server connections (Claude Code MCP Servers) |
/keybindings |
Opens ~/.claude/keybindings.json (Claude Code Keyboard Shortcuts) |
/statusline, /theme, /color, /output-style, /tui |
Change how Claude Code looks |
/import [codex|gemini|cursor] |
Brings in configuration from Codex, Gemini CLI or Cursor |
/sandbox |
Toggles sandbox mode |
Code review and GitHub
| Command | What it does |
|---|---|
/code-review (/review) |
Reviews the diff or a pull request for bugs; --fix applies findings, ultra runs a cloud review |
/security-review |
Checks the branch's changes for vulnerabilities |
/simplify |
Reviews changed code for cleanups and applies them |
/install-github-app |
Sets up the Claude GitHub App and Actions (Claude Code GitHub Actions) |
/autofix-pr |
Starts a cloud session that fixes CI failures and review comments on the branch's pull request |
Sessions, cloud and other surfaces
| Command | What it does |
|---|---|
/tasks |
Shows background work, including finished subagents |
/background |
Detaches the session to run in the background |
/teleport (/tp) |
Pulls a cloud session into the terminal (Claude Code on the Web) |
/remote-control |
Lets claude.ai or the phone app steer this session |
/desktop |
Continues the session in the desktop app (Claude Code Desktop) |
/schedule |
Creates or runs cloud scheduled tasks |
/loop [interval] [prompt] |
Repeats a prompt while the session is open |
/ide |
Connects to VS Code or a JetBrains IDE |
/chrome |
Configures Claude in Chrome |
/web-setup |
Connects GitHub for cloud sessions using your gh token |
Account, usage and help
| Command | What it does |
|---|---|
/usage (/cost, /stats) |
Shows session cost, plan limits and activity |
/usage-credits, /rate-limit-options, /upgrade |
Ways to keep working past a limit (Claude Code Pricing) |
/status |
Shows version, model, account and connectivity |
/login, /logout |
Signs in or out |
/doctor |
Checks the installation and setup and proposes fixes |
/help |
Lists commands |
/release-notes |
Browses the changelog |
/bug, /feedback |
Reports a problem or sends feedback |
/privacy-settings |
Shows and changes privacy settings |
/restart |
Restarts Claude Code to apply an update |
Bundled skills add more: /batch for large parallel changes, /debug, /claude-api, /run and /verify to launch and check your app, /design, /slides and /dataviz, /update-config and /fewer-permission-prompts. Lighter entries include /powerup (interactive lessons), /passes (share a free week of Claude Code), /radio (lo-fi music in the browser) and /stickers. All tables: Commands, read Nov 6, 2026.
How do I make a custom slash command?
Anthropic merged custom commands into skills: a file at .claude/commands/deploy.md and a skill at .claude/skills/deploy/SKILL.md both create /deploy and behave the same, and old command files keep working (Extend Claude with skills). If both exist with one name, the skill wins. Put it in the project's .claude/ to share it with everyone who clones the repository, or in ~/.claude/skills/ for yourself in every project.
---
name: fix-issue
description: Fix a GitHub issue
disable-model-invocation: true
---
Fix GitHub issue $ARGUMENTS following our coding standards.
With that file, /fix-issue 123 sends Claude the text with 123 in place of $ARGUMENTS (example from Extend Claude with skills). $0, $1 and so on take single arguments, and an arguments: list in the front matter gives them names. disable-model-invocation: true means only you can run it, which suits commands with side effects such as a deploy; without it, Claude may also use the skill on its own when the description fits. A line such as - PR diff: !`gh pr diff` runs the shell command first and pastes its output in. New or changed skills load without a restart, a behavior added in version 2.1.0 on Jan 7, 2026. MCP servers can add commands too, from the prompts they offer. More on How to Build a Claude Skill.
Frequently asked questions
How do I see all Claude Code commands? Type / at the start of the prompt, or run /help; Claude Code lists the commands, skills and MCP prompts available in that session.
What is the difference between /clear and /compact in Claude Code? /clear starts a new conversation with empty context, while /compact keeps the conversation but replaces its history with a summary to free space; it accepts instructions such as /compact keep the test output.
How do I undo changes in Claude Code? Run /rewind in Claude Code, or press Esc twice on an empty prompt, and pick the prompt to return to; it can restore code, conversation or both.
Where do custom slash commands go in Claude Code? Put them in .claude/skills/<name>/SKILL.md or .claude/commands/<name>.md in the project, or under ~/.claude/ to use them in every project.
What happened to /vim in Claude Code? The /vim command was removed in version 2.1.92; vim keys are now turned on in /config under Editor mode.
Why does Claude Code not run my slash command? Claude Code recognizes a command only at the very start of a message, and some commands are missing on certain platforms, plans or surfaces, such as cloud sessions, which lack /plugin and /resume.
Sources
- Commands, Claude Code Docs, read Nov 6, 2026
- Extend Claude with skills, Claude Code Docs, read Nov 6, 2026
- Use Claude Code in the cloud, Claude Code Docs, read Nov 6, 2026
- Claude Code changelog, Claude Code Docs, read Nov 6, 2026
- Context Management in Claude Code, Claude, May 18, 2026 (video)
- Building verification loops in Claude Code, Claude, Sep 25, 2026 (video)
- What are skills?, Claude, Feb 26, 2026 (video)
Moments
Context Management in Claude Code
Claude
Building verification loops in Claude Code
Claude
What are skills?
Claude
Related
-
Claude Agent SDKThe Claude Agent SDK (formerly the Claude Code SDK) is Anthropic's Python and TypeScript library that runs Claude Code's agent loop, tools, hooks, subagents and MCP support inside your own program; install it with pip install claude-agent-sdk or npm install @anthropic-ai/claude-agent-sdk.
-
Claude Code Best PracticesAnthropic's Claude Code best practices come down to three things: tell Claude what it cannot see in the code, give it a check to run that passes or fails, and enforce rules that cannot have exceptions with hooks and deny rules instead of CLAUDE.md lines.
-
Claude Code DesktopClaude Code Desktop is the Code tab of the Claude desktop app for macOS, Windows and Linux (beta). It runs Claude Code sessions side by side, locally, in the cloud or over SSH, with Git worktrees, a visual diff view, a terminal, a browser preview and computer use, on any paid Claude plan with no separate CLI install.
-
Claude Code GitHub ActionsClaude Code GitHub Actions (anthropics/claude-code-action@v1) lets you mention @claude in an issue or pull request to have Claude answer, change code and open pull requests; run /install-github-app in Claude Code to set it up.
-
Claude Code Headless and CIclaude -p "prompt" runs Claude Code once without the interactive screen and exits, printing text, JSON or streamed JSON; with --bare, --allowedTools and --permission-mode dontAsk it is how Claude Code runs in CI jobs, scripts and git hooks.
-
-
Claude Code Keyboard ShortcutsClaude Code's main shortcuts are Esc to stop Claude, Esc twice to rewind, Shift+Tab to cycle permission modes, Ctrl+R to search history, Ctrl+O for the transcript, Ctrl+B to background a task and Alt+P (Option+P) to switch model. Shortcuts can be changed in ~/.claude/keybindings.json, opened with /keybindings.
-
Claude Code MCP ServersClaude Code connects to MCP servers with claude mcp add, for example claude mcp add --transport http notion https://mcp.notion.com/mcp, stored per user, per project in a shared .mcp.json file, or locally for one project.
See also
-
-
-
Claude Code CheckpointsClaude Code saves a checkpoint of your files before every prompt, so /rewind or Esc pressed twice can restore the code, the conversation or both to an earlier point. Checkpoints cover Claude's own file edits, not changes made only by shell commands or most subagents, so Git is still needed.
-
CLAUDE.md and MemoryCLAUDE.md is a Markdown file of instructions that Claude Code loads at the start of every session, from your user folder (~/.claude/CLAUDE.md), the project (./CLAUDE.md) and a private CLAUDE.local.md; /init writes one. Claude Code also keeps an auto memory of what it learns, indexed in MEMORY.md, and reads AGENTS.md when there is no CLAUDE.md.
-
Claude Code Permissions and ModesClaude Code has six permission modes (Manual, Accept edits, Plan, Auto, Don't ask and Bypass permissions), cycled with Shift+Tab; since v2.1.283 interactive sessions start in auto mode, and --dangerously-skip-permissions turns every check off and belongs only in a container or VM.
-
Claude Code HooksClaude Code hooks are shell commands (or HTTP calls, MCP tools or model checks) that Claude Code runs at fixed points such as before a tool call, after an edit or when Claude stops, configured under "hooks" in a settings.json file.