SLASH COMMANDS

Log out of your active Google user session and wipe local authentication caches.

Fork the current conversation into a new thread with a fresh ID, leaving the original transcript untouched for parallel exploration.

Diagnose and verify your Claude Code installation and settings. Press f to have Claude fix any reported issues.

Choose a communication style for responses — friendly, pragmatic, or none — without rewriting your instructions.

Audit and clean up your Claude Code setup: unused skills, MCPs, and plugins, CLAUDE.md dedup and splitting, slow hooks, auto mode, and permission pre-approval. Confirms before making changes.

Attach a file or folder to the conversation via popup picker so Codex references it directly in the next turn.

Toggle visibility of reasoning blocks in the response.

Toggle or configure the visibility of real-time CLI diagnostic lines.

Archive the current session and exit. Removes it from active session lists; transcript kept locally. Restore with 'codex unarchive <SESSION>'.

Exit the active session and terminate agy safely. Alias: /quit.

List every other session Claude can message: local sessions on this machine and, when Remote Control is connected, your sessions on other machines and Claude Code on the web. Alias: /peers.

Summarize the visible conversation to free tokens. Use after long runs so Codex retains key points without blowing the context window.

Show the Git diff including files Git isn't tracking yet. Review Codex's edits before committing or running tests.

Generate an AGENTS.md scaffold in the current directory for persistent repo instructions.

Start an ephemeral side conversation for a focused detour — the parent thread keeps running and its status stays visible.

Sign out from Cursor.

Exit OpenCode. Aliases: /quit, /q. Keybind: Ctrl+x q.

Export the current conversation to Markdown and open in $EDITOR. Keybind: Ctrl+x x.

List available themes and switch the visual theme. Keybind: Ctrl+x t.

Clear the active terminal viewport and reset the screen buffer. Alias: /new.

Open the interactive configuration panel to adjust agent behaviors and CLI parameters. Alias: /settings.

Fork the current conversation thread into a new session, keeping original history intact. Alias: /branch.

Rewind conversation state to a previous point in history. Alias: /undo.

List all local project-scoped and global user-defined agent skills.

Review the current diff for correctness bugs and for reuse, simplification, and efficiency cleanups. Pass --fix to apply findings, --comment to post as GitHub PR comments, or ultra for a deep cloud review.

Set a persistent goal — Claude keeps working across turns until the condition is met. View, pause, resume, or clear with subcommands.

Manage MCP server connections and OAuth. v2.1.191 adds retries for capability discovery and OAuth token requests.

Create, update, list, or run Anthropic-managed cloud routines from the CLI. Alias: /routines.

View and manage background work in the current session. Stops from the tasks panel are permanent as of v2.1.191.

Choose the active model (and reasoning effort when available). Opens a picker; press s to switch for the current session only.

Set what Codex can do without asking first — switch between Auto, Read Only, or custom permission profiles mid-session.

Ask Codex to review your working tree — summarizes issues, focusing on behavior changes and missing tests.

Summarize conversation to free context window space while keeping a high-level record of what happened.

Toggle max mode on models that support it — enables extended reasoning and capability.

Start a new chat session with empty context.

Summarize the current session to save tokens. Alias: /summarize.

List available models across all configured providers. Keybind: Ctrl+x m.

Open the terminal-based interactive viewer for staged code artifacts and documents.

Route a task through Antigravity's deep-reasoning pipeline — higher token spend, multi-agent orchestration with execution and verification loops.

Ask a quick side-question or request info without starting a heavy agent execution state.

List all files, symbols, and references currently loaded inside the agent's context window.

Copy the last generated agent response directly to your host clipboard.

Display the current git diff of files modified by the agent in this session.

Toggle Fast Mode, modifying artificial typing delays and thought visualizations.

List all registered lifecycle hooks (e.g. pre-command, post-edit validations).

Configure or review keyboard shortcuts mapped to interactive TUI operations.

Change the default Gemini model used for the active reasoning conversation.

Manage fine-grained command and directory read/write authorization rules.

Open the interactive task board and execution step planner dashboard.

Resume or switch to a past conversation session. Aliases: /switch, /conversation.

Monitor, view output logs, or cancel active background tasks.

Orchestrate large-scale changes across a codebase in parallel. Decomposes work into 5–30 independent units, each in its own git worktree with its own PR.

Ask a quick side question without adding it to the main conversation history.

Start a new conversation with empty context. Previous session stays in /resume; use /rewind (v2.1.191+) to undo a clear in-session. Aliases: /reset, /new.

Research preview: generate a few editable UI artboards for a feature before you build it, then have Claude implement the one you pick.

Open an interactive diff viewer showing uncommitted changes and per-turn diffs. Navigate with arrow keys between the git diff and individual Claude turns.

Set the model effort level: low, medium, high, xhigh, max, or ultracode. Takes effect immediately without waiting for the current response.

Spawn a forked subagent that inherits the full conversation and works on a directive while you keep going in the main session.

Initialize project with a CLAUDE.md guide covering repo conventions, commands, and agent instructions.

Edit CLAUDE.md memory files, enable or disable auto-memory, and view auto-memory entries.

Rewind code and/or conversation to a checkpoint. As of v2.1.191, restore context from before /clear ran. Aliases: /checkpoint, /undo.

Analyze pending branch for security vulnerabilities — injection, auth issues, data exposure, and other OWASP risks.

Alias for /code-review ultra — multi-agent cloud code review fleet on a diff before merge.

Approve one retry of a recent auto review denial — lets Codex attempt a blocked action once under current policy.

Set a persistent task goal (max 4,000 chars). Codex tracks it across turns. Subcommands: pause, resume, clear, view.

Include open files, current selection, and other IDE context in the next prompt without re-explaining what's open.

Browse and use local skills to improve task-specific behavior by loading relevant skill context.

Create or edit custom slash commands for repetitive workflows.

Exit the Cursor CLI.

Resume a previous chat session by folder name.

Configure sandbox mode and network access settings for the current session.

Replace the current chat context with a summary to save tokens and free up context window space.

Manage MCP servers — list, describe, show schema, enable, disable, reload, or configure OAuth.

Reload memory from global, project, and subdirectory GEMINI.md files without restarting.

Manage folder trust settings. Trust a path so Gemini can operate there without per-action prompts.

Revert files to their pre-tool state using checkpointing. Pass a tool_call_id to restore a specific checkpoint.

Browse auto-saved sessions and manage manual checkpoints. Conversations are auto-saved; use tags for manual checkpoints.

Manage agent skills — list, enable, disable, or reload.

Toggle Vim mode for the composer. Saved to ~/.gemini/settings.json.

Restore a previously undone message and file changes. Git-backed. Keybind: Ctrl+x r.

List and switch sessions. Aliases: /resume, /continue. Keybind: Ctrl+x l.

Share the current session publicly.

Remove the last message and its responses, and revert any file changes made. Git-backed — requires a git repository. Keybind: Ctrl+x u.

Add a directory path to the active project workspace.

Open the subagents management panel to monitor and approve actions for background agents.

Display the latest product updates, version releases, and changelog info in the terminal.

Display the command cheatsheet, syntax help, and interactive keyboard guide.

Inspect active Model Context Protocol (MCP) servers and list their exposed tools.

Open the specified file directly inside your host's configured preferred text editor.

Rename the active conversation thread for better tracking and retrieval.

Toggle or customize the terminal emulator window title format.

Display current token count, model call pricing, and account limits. Alias: /quota.

Manage agent configurations and monitor background agents running in parallel.

Detach the current session to run as a background agent and free this terminal. Optionally pass a final instruction before detaching.

Load Claude API reference, migrate deprecated model IDs, or onboard Claude Managed Agents (schedules + vaults).

Free up context by summarizing the conversation so far. Optionally pass focus instructions for the summary.

Visualize current context usage as a colored grid. Shows optimization suggestions for context-heavy tools and capacity warnings.

View hook configurations for tool events. Comma-separated matchers like Bash,PowerShell work correctly as of v2.1.191.

Run a prompt repeatedly on a schedule while the session stays open. Omit the interval and Claude self-paces between iterations.

Switch the AI model and save it as your default for new sessions. Adjust effort level with left/right arrows on models that support it.