Codex Slash Commands: Complete CLI Reference (2026)

OpenAI Codex is OpenAI's agentic CLI for reading, editing, and running code in your repo—available in the terminal, desktop app, and cloud. Beyond natural-language prompts, it exposes 40+ built-in slash commands that switch models, adjust permissions, attach IDE context, spawn subagent threads, compact long conversations, and review your working tree without leaving the TUI.

This article is a complete slash-command reference, organized from the official Slash commands documentation. It is not a replacement for upstream docs: command availability, experimental flags, and catalog-driven features like /fast change with each release. Use this as a map of the surface area and a workflow guide; verify behavior against developers.openai.com/codex before you ship team runbooks.

For the Anthropic and Google equivalents, see Claude Code commands and Gemini CLI slash commands. For open-source multi-provider TUI, see OpenCode slash commands. For editor-parity terminal agent, see Cursor CLI slash commands.

TL;DR

How slash commands fit a typical workflow

OpenAI groups slash commands around session control—steering an active run without restarting Codex. The lifecycle below is the fastest way to learn the table.

flowchart LR
  A[Setup /init /permissions /mcp] --> B[Work /model /plan /goal]
  B --> C[Context /ide /mention /skills]
  C --> D[Parallel /agent /fork /side]
  D --> E[Ship /diff /review]
  E --> F[Sessions /new /clear /resume /archive]

First session in a repo

During a task

Context and attachments

Parallel work and subagents

See our goal mode guide for /goal patterns across Codex, Claude Code, and Hermes Agent.

Before you ship

Between sessions

Queuing commands during active tasks

When Codex is already working on a turn, slash commands behave differently than at idle:

1. Type the command and press Tab to queue it for the next turn.
2. Codex parses queued slash commands when they execute—menus and errors appear after the current turn finishes.
3. Slash completion still works before you queue the command.

Some commands are unavailable while a task runs: /plan, /archive, /copy (uses last completed output), and /side (also unavailable in review mode).

Setup, permissions, and project memory

/permissions vs /approve: /permissions changes the ongoing policy for what Codex can do without asking. /approve is a one-shot retry when the automatic reviewer denied a specific recent action.

Project memory: Codex uses AGENTS.md (via /init). Claude Code uses CLAUDE.md. Both solve the same problem—persistent repo instructions—under different filenames. See What is CLAUDE.md? for the Anthropic pattern and What is MEMORY.md? for the broader agent-memory hierarchy.

Model, speed, and communication style

/fast is catalog-driven. If the active model does not advertise a Fast tier, Codex will not expose /fast. Persist Fast settings when Codex offers to save them. Show Fast status in the footer via /statusline.

/personality is model-gated. If the active model does not support personality-specific instructions, Codex hides the command. Use none to disable personality instructions.

Planning, goals, and review mode

Goal length: Objectives must be non-empty and at most 4,000 characters. For longer instructions, put details in a file and point the goal at that file.

Plan mode: While a task is running, /plan is temporarily unavailable. For longer autonomous runs, pair /goal with verification loops—see loop engineering for cross-platform guardrails.

Review model: /review uses the current session model unless you set review_model in config.toml.

Session, context, and conversation control

/clear vs Ctrl+L: Ctrl+L clears the terminal view but keeps the current chat. /clear resets both the visible UI and the conversation. Codex disables both while a task is in progress.

/fork vs /side: /fork creates a durable parallel thread you can switch to via /agent or session management. /side is a temporary detour—you return to the parent thread when done. /side cannot nest inside another side conversation.

Archive restore: After /archive, run codex unarchive <SESSION> to restore. To fork a saved session (not the current one), use codex fork in the terminal.

Parallel agents and background terminals

Background terminals appear when unified_exec is in use; otherwise /ps may return an empty list. Enable subagents via /experimental if the feature picker includes them—restart when prompted.

For multi-agent orchestration patterns, see Claude Code dynamic workflows and OpenAI Codex plugins.

Review, diff, and shipping

Typical pre-commit flow:

/review
/diff

Codex focuses on behavior changes and missing tests. Follow /review with /diff when you need line-level inspection inside the CLI.

Skills, MCP, apps, plugins, and hooks

MCP: Use /mcp to confirm which external tools are available. Pass only verbose as an argument—anything else shows usage help.

Plugins vs apps: /plugins manages Codex plugin packages (tools, skills, MCP configs). /apps inserts connector mentions into the composer for immediate use.

For MCP fundamentals, see What is MCP?. For Codex plugin architecture, see OpenAI Codex plugins repository.

IDE, editor, and TUI customization

Persist defaults in config.toml:

Status-line items include model, model+reasoning, context stats, rate limits, git branch, token counters, session id, current directory, and Codex version.

Title items include app name, project, spinner, status, thread, git branch, model, and task progress.

Keymap bindings use names like ctrl-a, shift-enter, and page-down. Empty binding list unbinds an action.

Diagnostics and feedback

Use /debug-config when an effective setting differs from what you expect in config.toml. Output includes allowed_approval_policies, allowed_sandbox_modes, mcp_servers, rules, enforce_residency, and experimental_network when configured.

Complete command reference table

Every built-in slash command from the official Slash commands page as of June 2026.

Codex vs Claude Code: shared command patterns

Both agentic CLIs converged on a similar slash-command vocabulary in 2026. This table maps the most common equivalents:

Claude Code adds cloud orchestration (/batch, /background, /ultrareview), scheduled loops (/loop), and a larger settings surface. Codex adds /personality, /apps, /approve, /memories, and tighter TUI customization via /statusline and /title. Gemini CLI adds custom .toml slash commands, @ file injection, and ! shell passthrough.

Full references: Claude Code · Codex · Gemini CLI · OpenCode · Cursor CLI (five-way comparison in Cursor guide)

Commands worth memorizing first

Minimum viable slash stack for new Codex users:

/init                          # AGENTS.md scaffold
/permissions                   # trust boundaries
/model                         # pick the right model
/plan Propose a migration plan # think before large edits
/goal tests pass               # persistent target
/compact                       # free context mid-session
/diff                          # inspect edits
/review                        # second pass before commit
/resume                        # pick up yesterday's thread

For Codex desktop features beyond the CLI—pets, skills reload, MCP—see Codex pets complete guide and Codex plugins repository.

Related ExplainX guides

• Claude Code commands reference — Anthropic CLI counterpart
• Gemini CLI slash commands reference — Google CLI counterpart
• OpenCode slash commands reference — open-source TUI counterpart
• Cursor CLI slash commands reference — Cursor terminal counterpart
• Goal mode complete guide — /goal across Codex, Claude Code, Hermes
• Loop engineering — verification loops and guardrails
• What is MCP? — /mcp and external tools
• What are agent skills? — /skills authoring patterns
• OpenAI Codex plugins — plugin architecture
• Codex pets guide — desktop TUI extras
• Claude Code vs Codex — platform comparison
• AI coding plugins ecosystem — OpenAI vs Anthropic plugin stacks

Primary source: Slash commands — Codex Docs · Codex overview

Summary

Codex slash commands are the control plane for agentic coding in the terminal: they set trust (/permissions), project memory (/init → AGENTS.md), model and speed (/model, /fast), planning and goals (/plan, /goal), parallelism (/agent, /fork, /side), and quality gates (/diff, /review) without leaving the composer.

Type / to discover what your build exposes—availability varies by version, model catalog, and experimental flags. Treat the official Slash commands page as source of truth; bookmark this guide alongside Claude Code, Gemini CLI, OpenCode, and Cursor CLI command references.

Command names, aliases, and availability reflect OpenAI's documentation as of June 11, 2026. Re-check developers.openai.com/codex and the Codex changelog before documenting internal runbooks—OpenAI ships CLI updates frequently.