SLASH COMMANDS

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.

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

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.

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

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

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

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.

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.

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

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.

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.

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

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

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

Manage allow, ask, and deny rules for tool permissions. Recently-denied approvals persist on close as of v2.1.191.

Enter plan mode to design your approach before coding. Claude proposes an execution plan for review before any implementation starts.

Resume a previous conversation by ID or name, or open the session picker.

List available skills and manage which are shown to Claude. Press t to sort by token count, Space to hide a skill.

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

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

List configured Model Context Protocol (MCP) tools. Pass 'verbose' for server diagnostics.

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.

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

Switch to plan mode and optionally send a prompt. Codex proposes an execution plan before implementation starts.

Resume a saved conversation from your session list. Continue work from a previous CLI session without starting over.

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

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

Display session configuration and token usage — active model, approval policy, writable roots, and context capacity.

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

Switch to Plan mode — the agent researches your codebase, asks clarifying questions, and produces a reviewable implementation plan before writing code.

Resume a previous chat session by folder name.

Create new rules or edit existing rules in .cursor/rules (.mdc files) for persistent project guidance.

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

Analyze directory and generate a tailored GEMINI.md for persistent project memory.

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.

Switch to Plan Mode (read-only) where Gemini produces an approved plan before making any changes.

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

Navigate backward through history; revert chat and/or code to a prior state (also Esc Esc).

Add a provider and API key to connect a new AI model provider.

Open the external $EDITOR for composing messages — useful for long or structured prompts. Keybind: Ctrl+x e.

Guided AGENTS.md setup for the current project.

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

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