COMMAND REFERENCE▌

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.

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

Start a new conversation with empty context. The previous conversation stays available in /resume. Optionally name the previous conversation.

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.

View hook configurations for tool events — pre- and post-tool hooks that run shell commands around Claude's actions.

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.

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.

Rewind the conversation and/or code to a previous checkpoint, or summarize from a selected message.

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.