Codex CLI is open source and free to install. To use it, sign in with a ChatGPT plan or, after additional setup, an API key. Included usage and API costs depend on your account and model, so check the current OpenAI pricing and plan page before running production automation.

What's the difference between Codex CLI and the Codex App?

Codex CLI is the terminal tool you start with codex. It runs entirely in your shell and gives you the full set of commands, slash commands, and flags. The Codex App is a desktop application (macOS and Windows) with a graphical interface. The app has fewer slash commands but adds its own shortcuts, like Cmd+Shift+P for the command palette and Cmd+B for the sidebar. Both use the same models and the same configuration.

Which model should I use with Codex?

Choose a model for the task and the access available to you. Current Codex documentation uses gpt-5.6-sol, gpt-5.6-terra, and gpt-5.6-luna as examples. Open /model to see the models and reasoning effort available in your account, or use -m to set a model for a single run.

What's the difference between codex exec and interactive codex?

codex starts an interactive TUI session where you can chat back and forth with the agent. codex exec runs a task non-interactively: it takes a prompt, works through it, and prints the result to stdout. codex exec is ideal for scripts, CI/CD pipelines, and automation.

How do I resume a previous session?

Inside the interactive TUI, type /resume, or run codex resume from the terminal. For non-interactive use, run codex exec resume --last followed by your new prompt. Sessions started with --ephemeral are not saved. Use codex archive to clean up the picker, codex unarchive to restore an archived session, and codex delete to remove one permanently.

What does the sandbox actually do?

The sandbox limits what Codex can do on your system. read-only allows reading only (no file changes, no network). workspace-write allows write access in the working directory only (no network). danger-full-access allows everything: reading, writing anywhere, and network access. workspace-write is enough for most tasks.

Can I use Codex CLI in my CI/CD pipeline?

Yes. Use codex -a never exec -s workspace-write for automated execution without prompts. The approval flag is global and must appear before exec. With --json you get structured JSONL output. Authenticate with an API key: echo $OPENAI_API_KEY | codex login --with-api-key. Add --skip-git-repo-check if you're running outside a Git repo.

How does Codex differ from Claude Code?

Both are terminal-based AI coding agents. Codex uses OpenAI's GPT models, Claude Code uses Anthropic's Claude models. Codex has especially strong cloud integration (Codex Cloud for remote tasks) and a standalone desktop app alongside the CLI. Claude Code is more terminal-first and adds features like native Git worktrees, hooks, and Extended Thinking. For a detailed comparison, see our article Claude Code vs. OpenAI Codex.

Codex Commands: The Complete Reference

You installed Codex, typed codex into your terminal, and wondered: "Okay, now what?"

Same here. OpenAI's coding agent evolves quickly. Commands for sessions, plugins, Cloud, and remote control are added while others change. Without a current reference, you lose track fast.

This article lays out every Codex command in one place. Each CLI command, every slash command, all flags, every keyboard shortcut for CLI and App. It's the most thorough Codex reference you'll find in English. If you'd rather compare Codex head-to-head with Claude Code, our in-depth Claude Code vs. OpenAI Codex comparison has you covered.

TL;DRKey Takeaways

This reference covers the current CLI, from codex exec and codex review to session archives, plugins, the app server, and Codex Cloud
Slash commands in the composer control the model, permissions, sessions, plan mode, and other TUI features. The table lists the introduction version for all 53 commands
Three sandbox modes (read-only, workspace-write, danger-full-access) and three approval policies control what Codex can do on your system
Codex Cloud can run work in remote environments. App-server and remote-control are clearly marked experimental

Installing and Starting Codex

Codex CLI installs via npm or Homebrew. On first launch, Codex asks you to sign in with your ChatGPT account or an API key.

# Install via npm
npm install -g @openai/codex

# Or via Homebrew
brew install --cask codex

# Sign in interactively (opens browser for OAuth)
codex login

# Sign in with an API key
echo $OPENAI_API_KEY | codex login --with-api-key

# Check login status
codex login status

# Sign out
codex logout

# Start an interactive TUI session
codex

# Start with an initial prompt
codex "Explain the architecture of this project"

# Run non-interactively (for scripts)
codex exec -s workspace-write -m gpt-5.6-terra "Refactor auth.ts"

# Launch the desktop app
codex app

Tip

Always start Codex inside the right project folder. You can also set the working directory explicitly with --cd /path/to/project.

CLI Commands (Overview)

Codex comes in two flavors. The CLI runs in your terminal. The App is a desktop application for macOS and Windows. The "Example" column shows the typical usage of each command.

Commandcodex

DescriptionStart an interactive TUI session in the terminal

Examplecodex

Commandcodex app

DescriptionLaunch the Codex desktop app (macOS/Windows)

Examplecodex app

Commandcodex agents

DescriptionBrowse agent sessions on the local app-server daemon

Examplecodex agents

Commandcodex app-server

DescriptionExperimental: start the app server for development, debugging, or remote connections

Examplecodex app-server --listen ws://127.0.0.1:4500

Commandcodex apply

DescriptionApply the latest diff from a Codex agent locally

Examplecodex apply TASK_ID

Commandcodex archive

DescriptionArchive a saved session without deleting its transcript

Examplecodex archive SESSION

Commandcodex cloud

DescriptionExperimental: browse Cloud tasks or run them from the terminal

Examplecodex cloud list

Commandcodex exec

DescriptionRun a task non-interactively, stream output to stdout

Examplecodex exec "Fix bug"

Commandcodex exec resume

DescriptionResume a previous session non-interactively

Examplecodex exec resume --last "Continue task"

Commandcodex exec fork

DescriptionFork a previous session into a new thread non-interactively

Examplecodex exec fork --last "Try an alternative"

Commandcodex exec-server

DescriptionExperimental: start the exec server for remote environments

Examplecodex exec-server --listen ws://127.0.0.1:8787

Commandcodex review

DescriptionCode review (uncommitted, branch diff, or commit)

Examplecodex review --uncommitted

Commandcodex resume

DescriptionResume an interactive session (session picker)

Examplecodex resume

Commandcodex fork

DescriptionFork a session into a new thread

Examplecodex fork

Commandcodex unarchive

DescriptionRestore an archived session

Examplecodex unarchive SESSION

Commandcodex delete

DescriptionPermanently delete a saved session

Examplecodex delete SESSION

Commandcodex cloud exec

DescriptionSubmit a cloud task in a sandbox environment

Examplecodex cloud exec --env ENV_ID "..."

Commandcodex cloud list

DescriptionList cloud tasks (with filter and pagination)

Examplecodex cloud list

Commandcodex cloud status

DescriptionShow the status of a cloud task

Examplecodex cloud status ID

Commandcodex cloud diff

DescriptionShow the diff of a cloud task

Examplecodex cloud diff ID

Commandcodex cloud apply

DescriptionApply a cloud task diff locally

Examplecodex cloud apply ID

Commandcodex debug

DescriptionExperimental diagnostics for the model catalog, prompt input, and app server

Examplecodex debug models --bundled

Commandcodex doctor

DescriptionCheck installation, configuration, sign-in, runtime, and Git health

Examplecodex doctor --summary

Commandcodex mcp

DescriptionManage external MCP servers

Examplecodex mcp list

Commandcodex mcp add

DescriptionAdd an MCP server (stdio or HTTP)

Examplecodex mcp add name -- cmd

Commandcodex mcp list

DescriptionList configured MCP servers

Examplecodex mcp list

Commandcodex mcp get

DescriptionShow an MCP server's configuration

Examplecodex mcp get name

Commandcodex mcp remove

DescriptionRemove an MCP server

Examplecodex mcp remove name

Commandcodex mcp login

DescriptionOAuth login for an MCP server

Examplecodex mcp login name

Commandcodex mcp logout

DescriptionRemove an MCP server's OAuth credentials

Examplecodex mcp logout name

Commandcodex features list

DescriptionShow feature flags with status and maturity

Examplecodex features list

Commandcodex features enable/disable

DescriptionEnable or disable a feature flag persistently

Examplecodex features enable NAME

Commandcodex login

DescriptionSign in via OAuth or API key

Examplecodex login

Commandcodex login status

DescriptionShow the current login status

Examplecodex login status

Commandcodex logout

DescriptionRemove stored credentials

Examplecodex logout

Commandcodex sandbox

DescriptionRun a command in the Codex sandbox (macOS/Linux/Windows)

Examplecodex sandbox -- cmd

Commandcodex completion

DescriptionGenerate shell completions (bash, zsh, fish, elvish, PowerShell)

Examplecodex completion zsh

Commandcodex update

DescriptionCheck for updates and install the new version

Examplecodex update

Commandcodex execpolicy

DescriptionCheck exec-policy rule files before saving

Examplecodex execpolicy check --rules rules.toml -- npm test

Commandcodex mcp-server

DescriptionRun Codex itself as an MCP server (stdio transport)

Examplecodex mcp-server

Commandcodex plugin

DescriptionInstall, list, or remove plugins from configured marketplaces

Examplecodex plugin list

Commandcodex plugin marketplace

DescriptionManage plugin marketplace sources (add, remove, upgrade)

Examplecodex plugin marketplace add URL

Commandcodex remote-control

DescriptionExperimental: start, stop, or pair the remotely controllable app-server daemon

Examplecodex remote-control pair

Commandcodex queue

DescriptionQueue a message for an existing local session

Examplecodex queue --thread SESSION --message "Continue with the tests"

Commandcodex migrate-rollouts

DescriptionInspect or migrate older local sessions to paginated thread history

Examplecodex migrate-rollouts --verbose

	Description	Example
`codex`	Start an interactive TUI session in the terminal	`codex`
`codex app`	Launch the Codex desktop app (macOS/Windows)	`codex app`
`codex agents`	Browse agent sessions on the local app-server daemon	`codex agents`
`codex app-server`	Experimental: start the app server for development, debugging, or remote connections	`codex app-server --listen ws://127.0.0.1:4500`
`codex apply`	Apply the latest diff from a Codex agent locally	`codex apply TASK_ID`
`codex archive`	Archive a saved session without deleting its transcript	`codex archive SESSION`
`codex cloud`	Experimental: browse Cloud tasks or run them from the terminal	`codex cloud list`
`codex exec`	Run a task non-interactively, stream output to stdout	`codex exec "Fix bug"`
`codex exec resume`	Resume a previous session non-interactively	`codex exec resume --last "Continue task"`
`codex exec fork`	Fork a previous session into a new thread non-interactively	`codex exec fork --last "Try an alternative"`
`codex exec-server`	Experimental: start the exec server for remote environments	`codex exec-server --listen ws://127.0.0.1:8787`
`codex review`	Code review (uncommitted, branch diff, or commit)	`codex review --uncommitted`
`codex resume`	Resume an interactive session (session picker)	`codex resume`
`codex fork`	Fork a session into a new thread	`codex fork`
`codex unarchive`	Restore an archived session	`codex unarchive SESSION`
`codex delete`	Permanently delete a saved session	`codex delete SESSION`
`codex cloud exec`	Submit a cloud task in a sandbox environment	`codex cloud exec --env ENV_ID "..."`
`codex cloud list`	List cloud tasks (with filter and pagination)	`codex cloud list`
`codex cloud status`	Show the status of a cloud task	`codex cloud status ID`
`codex cloud diff`	Show the diff of a cloud task	`codex cloud diff ID`
`codex cloud apply`	Apply a cloud task diff locally	`codex cloud apply ID`
`codex debug`	Experimental diagnostics for the model catalog, prompt input, and app server	`codex debug models --bundled`
`codex doctor`	Check installation, configuration, sign-in, runtime, and Git health	`codex doctor --summary`
`codex mcp`	Manage external MCP servers	`codex mcp list`
`codex mcp add`	Add an MCP server (stdio or HTTP)	`codex mcp add name -- cmd`
`codex mcp list`	List configured MCP servers	`codex mcp list`
`codex mcp get`	Show an MCP server's configuration	`codex mcp get name`
`codex mcp remove`	Remove an MCP server	`codex mcp remove name`
`codex mcp login`	OAuth login for an MCP server	`codex mcp login name`
`codex mcp logout`	Remove an MCP server's OAuth credentials	`codex mcp logout name`
`codex features list`	Show feature flags with status and maturity	`codex features list`
`codex features enable/disable`	Enable or disable a feature flag persistently	`codex features enable NAME`
`codex login`	Sign in via OAuth or API key	`codex login`
`codex login status`	Show the current login status	`codex login status`
`codex logout`	Remove stored credentials	`codex logout`
`codex sandbox`	Run a command in the Codex sandbox (macOS/Linux/Windows)	`codex sandbox -- cmd`
`codex completion`	Generate shell completions (bash, zsh, fish, elvish, PowerShell)	`codex completion zsh`
`codex update`	Check for updates and install the new version	`codex update`
`codex execpolicy`	Check exec-policy rule files before saving	`codex execpolicy check --rules rules.toml -- npm test`
`codex mcp-server`	Run Codex itself as an MCP server (stdio transport)	`codex mcp-server`
`codex plugin`	Install, list, or remove plugins from configured marketplaces	`codex plugin list`
`codex plugin marketplace`	Manage plugin marketplace sources (add, remove, upgrade)	`codex plugin marketplace add URL`
`codex remote-control`	Experimental: start, stop, or pair the remotely controllable app-server daemon	`codex remote-control pair`
`codex queue`	Queue a message for an existing local session	`codex queue --thread SESSION --message "Continue with the tests"`
`codex migrate-rollouts`	Inspect or migrate older local sessions to paginated thread history	`codex migrate-rollouts --verbose`

Note

codex exec is the command you'll use most for automation. It runs tasks non-interactively and prints the result to stdout. Perfect for scripts and CI/CD pipelines.

codex exec: Flags for Non-Interactive Execution

codex exec is your workhorse for automated workflows. Set the sandbox and approval policy deliberately, so a scripted run behaves predictably and its access remains clear.

# Standard pattern for automated execution
codex -a never exec -s workspace-write -m gpt-5.6-terra "your prompt"

# Maximum reasoning depth
codex -a on-request exec -s workspace-write -m gpt-5.6-sol \
  -c model_reasoning_effort='"xhigh"' "complex task"

# Read-only for analysis (no file changes)
codex exec -s read-only -m gpt-5.6-luna "Analyze the architecture"

Flag--model, -m

DescriptionOverrides the model from your config

Example-m gpt-5.6-terra

Flag--sandbox, -s

DescriptionSandbox mode: read-only, workspace-write, or danger-full-access

Example-s workspace-write

FlagGlobal: --ask-for-approval, -a

DescriptionSets on-request or never and must appear before the exec subcommand

Examplecodex -a on-request exec "..."

Flag--cd, -C

DescriptionSets the working directory for the agent

Example-C /path/to/project

Flag--add-dir

DescriptionGrants additional writable directories

Example--add-dir ../backend

Flag--image, -i

DescriptionAttaches images to the prompt (repeatable)

Example-i screenshot.png

Flag--config, -c

DescriptionOverrides config.toml values (TOML syntax)

Example-c model_reasoning_effort='"xhigh"'

Flag--profile, -p

DescriptionLoads a named config profile from config.toml

Example-p fast-profile

Flag--enable / --disable

DescriptionEnables or disables a feature flag for this run

Example--enable search_tool

Flag--json

DescriptionOutputs events as JSONL (one JSON line per event)

Examplecodex exec --json "..."

Flag--output-last-message, -o

DescriptionSaves the agent's last message to a file

Example-o /tmp/result.txt

Flag--output-schema

DescriptionJSON Schema file that constrains the final response

Example--output-schema schema.json

Flag--ephemeral

DescriptionSession is not persisted to disk

Examplecodex exec --ephemeral "..."

Flag--skip-git-repo-check

DescriptionAllows running outside a Git repo

Examplecodex exec --skip-git-repo-check "..."

Flag--color

DescriptionControls ANSI colors: always, never, auto

Example--color never

Flag--oss

DescriptionUses a local open-source model provider

Examplecodex exec --oss "..."

Flag--local-provider

DescriptionExplicitly selects LM Studio or Ollama with --oss

Example--oss --local-provider ollama

Flag--strict-config

DescriptionFails when config.toml contains fields this Codex version does not recognize

Examplecodex exec --strict-config "..."

Flag--ignore-user-config

DescriptionDoes not load user config.toml but keeps authentication available

Examplecodex exec --ignore-user-config "..."

Flag--ignore-rules

DescriptionDoes not load user or project exec-policy rules

Examplecodex exec --ignore-rules "..."

Flag--dangerously-bypass-approvals-and-sandbox, --yolo

DescriptionBypasses approvals and the sandbox entirely. Use only inside an externally hardened environment.

Examplecodex exec --yolo "..."

Flag--approve-for-me

DescriptionRoutes approval requests through automatic review using the workspace-write sandbox

Examplecodex exec --approve-for-me "..."

Flag--dangerously-bypass-hook-trust

DescriptionRuns enabled hooks without persisted trust. Use only for already vetted automation.

Examplecodex exec --dangerously-bypass-hook-trust "..."

Flag	Description	Example
`--model, -m`	Overrides the model from your config	`-m gpt-5.6-terra`
`--sandbox, -s`	Sandbox mode: read-only, workspace-write, or danger-full-access	`-s workspace-write`
`Global: --ask-for-approval, -a`	Sets on-request or never and must appear before the exec subcommand	`codex -a on-request exec "..."`
`--cd, -C`	Sets the working directory for the agent	`-C /path/to/project`
`--add-dir`	Grants additional writable directories	`--add-dir ../backend`
`--image, -i`	Attaches images to the prompt (repeatable)	`-i screenshot.png`
`--config, -c`	Overrides config.toml values (TOML syntax)	`-c model_reasoning_effort='"xhigh"'`
`--profile, -p`	Loads a named config profile from config.toml	`-p fast-profile`
`--enable / --disable`	Enables or disables a feature flag for this run	`--enable search_tool`
`--json`	Outputs events as JSONL (one JSON line per event)	`codex exec --json "..."`
`--output-last-message, -o`	Saves the agent's last message to a file	`-o /tmp/result.txt`
`--output-schema`	JSON Schema file that constrains the final response	`--output-schema schema.json`
`--ephemeral`	Session is not persisted to disk	`codex exec --ephemeral "..."`
`--skip-git-repo-check`	Allows running outside a Git repo	`codex exec --skip-git-repo-check "..."`
`--color`	Controls ANSI colors: always, never, auto	`--color never`
`--oss`	Uses a local open-source model provider	`codex exec --oss "..."`
`--local-provider`	Explicitly selects LM Studio or Ollama with --oss	`--oss --local-provider ollama`
`--strict-config`	Fails when config.toml contains fields this Codex version does not recognize	`codex exec --strict-config "..."`
`--ignore-user-config`	Does not load user config.toml but keeps authentication available	`codex exec --ignore-user-config "..."`
`--ignore-rules`	Does not load user or project exec-policy rules	`codex exec --ignore-rules "..."`
`--dangerously-bypass-approvals-and-sandbox, --yolo`	Bypasses approvals and the sandbox entirely. Use only inside an externally hardened environment.	`codex exec --yolo "..."`
`--approve-for-me`	Routes approval requests through automatic review using the workspace-write sandbox	`codex exec --approve-for-me "..."`
`--dangerously-bypass-hook-trust`	Runs enabled hooks without persisted trust. Use only for already vetted automation.	`codex exec --dangerously-bypass-hook-trust "..."`

Warning

--yolo aliases --dangerously-bypass-approvals-and-sandbox. It bypasses both approvals and sandboxing. Use it only inside an externally hardened environment.

Common Patterns

# Attach images (screenshots, design specs)
codex exec -s workspace-write -m gpt-5.6-terra -i screenshot.png "Implement this UI"

# Multiple writable directories
codex exec -s workspace-write -C apps/frontend --add-dir ../backend "Sync API types"

# JSON output for scripts
codex exec -s workspace-write --json "List all TODO comments"

# Save the result to a file
codex exec -s workspace-write -o /tmp/result.txt "Summarize this codebase"

# Structured output with JSON Schema
codex exec -s workspace-write --output-schema schema.json "Extract all API endpoints"

# Pipe the prompt via stdin
cat prompt.txt | codex exec -s workspace-write -

# Use a config profile
codex exec -s workspace-write -p thorough "Thorough analysis"

# Local open-source model (Ollama or LM Studio)
codex exec --oss --local-provider ollama -s workspace-write "Explain this function"

# Strictly validate config before an automated run
codex exec --strict-config -s workspace-write "Check the configuration"

Code Review

codex review analyzes code changes non-interactively and prints the results to stdout. It doesn't modify files.

Flag--uncommitted

DescriptionReviews staged, unstaged, and untracked changes

Examplecodex review --uncommitted

Flag--base

DescriptionReviews changes against a base branch

Examplecodex review --base main

Flag--commit

DescriptionReviews a specific commit

Examplecodex review --commit abc123

Flag--title

DescriptionOptional title for the review summary

Examplecodex review --title "Add auth"

FlagPROMPT

DescriptionCustom review instructions (can also be piped via stdin with -)

Examplecodex review "Focus on security"

Flag	Description	Example
`--uncommitted`	Reviews staged, unstaged, and untracked changes	`codex review --uncommitted`
`--base`	Reviews changes against a base branch	`codex review --base main`
`--commit`	Reviews a specific commit	`codex review --commit abc123`
`--title`	Optional title for the review summary	`codex review --title "Add auth"`
`PROMPT`	Custom review instructions (can also be piped via stdin with -)	`codex review "Focus on security"`

# Review uncommitted changes (staged + unstaged + untracked)
codex review --uncommitted

# Review changes against a branch (before opening a PR)
codex review --base main

# Review a specific commit
codex review --commit abc123

# Review a commit with a title
codex review --commit abc123 --title "Add auth"

# Review with a custom focus
codex review "Focus on security"

# Review via exec with JSON output
codex exec review --uncommitted --json

Session Management

Codex stores non-ephemeral sessions locally. You can resume, fork, archive, or pick them up non-interactively.

# Interactive: open the session picker
codex resume

# Interactive: resume the most recent session directly
codex resume --last

# Non-interactive: resume the latest session with a new prompt
codex exec resume --last -s workspace-write -m gpt-5.6-terra \
  "Now add error handling"

# Resume a specific session by UUID
codex exec resume 7f9f9a2e-1b3c-4c7a... -s workspace-write -m gpt-5.6-terra \
  "Implement the plan"

# Fork a session (new thread from existing context)
codex fork --last

# Archive or restore a session
codex archive SESSION
codex unarchive SESSION

# Permanently delete a session
codex delete SESSION

# Apply a diff from a local session
codex apply TASK_ID

# Apply a diff from a cloud task
codex cloud apply TASK_ID

# Apply a specific attempt (when using --attempts N)
codex cloud apply TASK_ID --attempt 2

Tip

Sessions started with --ephemeral aren't saved to disk. Use this for quick one-off questions where you don't need any history.

Codex Cloud

Codex Cloud works with remote environments. Without a subcommand, codex cloud opens a picker. codex cloud exec submits a task directly, and requires --env.

Flag--env

DescriptionRequired: target environment ID for the cloud task

Example--env ENV_ID

Flag--attempts

DescriptionNumber of attempts (best-of-N), default: 1

Example--attempts 3

Flag--branch

DescriptionGit branch the task should run on

Example--branch feature/auth

Flag--json

DescriptionMachine-readable JSON output (for codex cloud list)

Examplecodex cloud list --json

Flag--limit

DescriptionMaximum number of tasks returned (1-20)

Examplecodex cloud list --limit 5

Flag--cursor

DescriptionPagination cursor from the previous call

Examplecodex cloud list --cursor CURSOR

Flag--attempt

DescriptionAttempt number for diff/apply (when using --attempts N)

Examplecodex cloud diff TASK_ID --attempt 2

Flag	Description	Example
`--env`	Required: target environment ID for the cloud task	`--env ENV_ID`
`--attempts`	Number of attempts (best-of-N), default: 1	`--attempts 3`
`--branch`	Git branch the task should run on	`--branch feature/auth`
`--json`	Machine-readable JSON output (for codex cloud list)	`codex cloud list --json`
`--limit`	Maximum number of tasks returned (1-20)	`codex cloud list --limit 5`
`--cursor`	Pagination cursor from the previous call	`codex cloud list --cursor CURSOR`
`--attempt`	Attempt number for diff/apply (when using --attempts N)	`codex cloud diff TASK_ID --attempt 2`

# Submit a task
codex cloud exec --env ENV_ID "Refactor the payment module"

 # Best-of-3: run three attempts
 codex cloud exec --env ENV_ID --attempts 3 "Fix the flaky test"

# Run on a specific branch
codex cloud exec --env ENV_ID --branch feature/auth "Add OAuth"

# List tasks
 codex cloud list
codex cloud list --json --limit 5

# Check the status
codex cloud status TASK_ID

# Show the diff (specific attempt)
codex cloud diff TASK_ID --attempt 2

App Server and Remote Control

App-server, remote connections, and remote-control are experimental. They are for advanced setups and may change between releases. You do not need them for everyday Codex work.

# Start an app server with a WebSocket endpoint
codex app-server --listen ws://127.0.0.1:4500

# Connect the TUI to an app server
codex --remote ws://127.0.0.1:4500

# Manage the remote-control daemon
codex remote-control start
codex remote-control pair
codex remote-control stop

# Diagnose the model catalog and local installation
codex debug models --bundled
codex doctor --summary

Sandbox Modes

The sandbox limits what Codex can do on your system. You pick the mode with -s or --sandbox.

Moderead-only

ReadAnywhere

WriteNowhere

NetworkNo

When to useQuestions, explanations, code analysis

Modeworkspace-write

ReadAnywhere

WriteWorking dir only

NetworkNo

When to useDefault for most tasks

Modedanger-full-access

ReadAnywhere

WriteAnywhere

NetworkYes

When to useOnly when truly needed (e.g., installing packages)

Mode	Read	Write	Network	When to use
`read-only`	Anywhere	Nowhere	No	Questions, explanations, code analysis
`workspace-write`	Anywhere	Working dir only	No	Default for most tasks
`danger-full-access`	Anywhere	Anywhere	Yes	Only when truly needed (e.g., installing packages)

Codex also ships with a codex sandbox command that lets you run any command inside the sandbox without involving the agent:

# Run a command in the current Codex sandbox
codex sandbox -- npm test

# Log denied accesses on macOS
codex sandbox --log-denials -- ./build.sh

# Set a project folder as the working directory
codex sandbox -C apps/frontend -- npm test

Approval Policies

Approval policies control when Codex asks for permission before running a command. Set the global -a or --ask-for-approval flag before the subcommand, for example codex -a on-request exec.

Policyon-request

BehaviorThe model decides when to ask for approval

Policynever

BehaviorNever asks for approval; failures go straight back to the model

Policy	Behavior
`on-request`	The model decides when to ask for approval
`never`	Never asks for approval; failures go straight back to the model

Note

Inside the interactive TUI you switch approval mode with /permissions. Three presets are available: Auto (default), Read Only, and Full Access.

MCP Servers (Model Context Protocol)

Codex can connect to MCP servers for extra tools (databases, APIs, GitHub, and more). All management commands are non-interactive.

# List configured servers
codex mcp list
codex mcp list --json

# Show a server's config
codex mcp get my-server
codex mcp get my-server --json

# Add a stdio server
codex mcp add my-server -- npx -y @my/mcp-server
codex mcp add my-server --env API_KEY=sk-123 -- node server.js

# Add an HTTP server
codex mcp add my-server --url https://mcp.example.com/sse
codex mcp add my-server --url https://mcp.example.com \
  --bearer-token-env-var MY_TOKEN_VAR

# Remove a server
codex mcp remove my-server

# OAuth login for an MCP server
codex mcp login my-server --scopes "read,write"
codex mcp logout my-server

Tip

With codex mcp-server you can run Codex itself as an MCP server. That makes it possible to plug Codex into other tools that speak MCP.

Slash Commands (CLI and App)

Slash commands are available in the interactive TUI (started with codex) and in the desktop app. Type / in the composer to open the list. While a task is running, you can type a slash command and press Tab to queue it for the next turn.

The CLI TUI has more slash commands than the app. The table lists currently documented commands, parameters, and their introduction versions. Individual commands may be unavailable depending on your platform, model, or enabled features.

I checked more than the release notes for this column. It lists the earliest regular Codex release whose source tree exposes the specific slash command. Renames such as /autoreview to /approve count from the version that introduced the new name.

Command/agents

Parameter

Since version0.149

DescriptionView and switch between all active agent sessions

Command/app

Parameter

Since version0.138

DescriptionOpen the current session in the desktop app

Command/apps

Parameter

Since version0.93

DescriptionBrowse apps and insert one into the prompt

Command/approve

Parameter

Since version0.129

DescriptionApprove one retry after an auto-review denial

Command/archive

Parameter

Since version0.136

DescriptionArchive the current session and exit Codex

Command/cd

Parameteroptional path

Since version0.149

DescriptionChange the current working directory

Command/clear

Parameteroptional name

Since version0.105

DescriptionClear the terminal and start a fresh chat

Command/compact

Parameter

Since version0.11

DescriptionSummarize the visible conversation to free context

Command/copy

Parameter

Since version0.105

DescriptionCopy the latest completed output (also Ctrl+O)

Command/debug-config

Parameter

Since version0.97

DescriptionPrint configuration layers and requirements diagnostics

Command/delete

Parameter

Since version0.140

DescriptionPermanently delete the current session and its child sessions

Command/diff

Parameter

Since version0.2

DescriptionShow the Git diff, including untracked files

Command/exit

Parameter

Since version0.53

DescriptionExit the CLI (alias /quit)

Command/experimental

Parameter

Since version0.74

DescriptionToggle experimental features

Command/export

Parameteroptional destination path

Since version0.148

DescriptionExport the conversation as Markdown

Command/fast

Parameter

Since version0.110

DescriptionToggle the Fast service tier when the active model offers one

Command/feedback

Parameter

Since version0.47

DescriptionSend diagnostic logs to the Codex maintainers

Command/fork

Parameter

Since version0.81

DescriptionFork the current conversation into a new chat

Command/goal

Parametergoal | edit | pause | resume | clear

Since version0.128

DescriptionSet, edit, pause, or clear a task goal

Command/hooks

Parameter

Since version0.129

DescriptionView and manage lifecycle hooks

Command/ide

Parameteroptional text

Since version0.129

DescriptionInclude open files, selection, and IDE context

Command/import

Parameter

Since version0.140

DescriptionImport supported Claude Code or Cursor setup, projects, and chats

Command/init

Parameter

Since version0.14

DescriptionGenerate an AGENTS.md scaffold for project context

Command/keymap

Parameter

Since version0.128

DescriptionRemap TUI keyboard shortcuts

Command/logout

Parameter

Since version0.15

DescriptionSign out of Codex

Command/mcp

Parameterverbose

Since version0.23

DescriptionList configured MCP tools

Command/memories

Parameter

Since version0.121

DescriptionConfigure memory use and generation

Command/mention

Parameterpath

Since version0.21

DescriptionAttach a file or folder to the conversation

Command/model

Parametermodel

Since version0.23

DescriptionChoose the active model and, when available, reasoning effort

Command/new

Parameteroptional name

Since version0.2

DescriptionStart a new chat in the same CLI session

Command/permissions

Parameter

Since version0.89

DescriptionSet what Codex can do without asking first

Command/personality

Parameter

Since version0.92

DescriptionChoose a communication style for responses

Command/pets

Parameter

Since version0.131

DescriptionChoose or hide a terminal pet (alias /pet)

Command/plan

Parameteroptional prompt

Since version0.93

DescriptionSwitch to plan mode

Command/plugins

Parameter

Since version0.117

DescriptionBrowse installed and discoverable plugins

Command/ps

Parameter

Since version0.76

DescriptionShow background terminals and their recent output

Command/pwd

Parameter

Since version0.149

DescriptionShow the current working directory (alias /cwd)

Command/raw

Parameteron | off

Since version0.129

DescriptionToggle raw scrollback mode

Command/rename

Parameteroptional name

Since version0.93

DescriptionRename the current chat

Command/resume

Parameter

Since version0.65

DescriptionResume a saved session from the session picker

Command/review

Parameter

Since version0.39

DescriptionAsk Codex to review the working tree

Command/sandbox-add-read-dir

Parameterabsolute path

Since version0.102

DescriptionGrant sandbox read access to a directory (Windows only)

Command/setup-default-sandbox

Parameter

Since version0.100

DescriptionSet up the elevated default sandbox (Windows only)

Command/side

Parameteroptional text

Since version0.122

DescriptionStart an ephemeral side conversation in a temporary fork (alias /btw)

Command/skills

Parameter

Since version0.65

DescriptionBrowse and use skills

Command/status

Parameter

Since version0.14

DescriptionShow the model, approval policy, writable roots, and token usage

Command/statusline

Parameter

Since version0.99

DescriptionConfigure TUI status-line fields

Command/stop

Parameter

Since version0.115

DescriptionStop all background terminals (alias /clean)

Command/subagents

Parameter

Since version0.115

DescriptionSwitch between this session's subagents

Command/theme

Parameter

Since version0.105

DescriptionChoose a syntax-highlighting theme

Command/title

Parameter

Since version0.117

DescriptionConfigure terminal-title fields

Command/usage

Parameterdaily | weekly | cumulative

Since version0.140

DescriptionView account token usage or request a rate-limit reset

Command/vim

Parameter

Since version0.129

DescriptionToggle Vim mode for the composer

	Parameter		Description
`/agents`		0.149	View and switch between all active agent sessions
`/app`		0.138	Open the current session in the desktop app
`/apps`		0.93	Browse apps and insert one into the prompt
`/approve`		0.129	Approve one retry after an auto-review denial
`/archive`		0.136	Archive the current session and exit Codex
`/cd`	optional path	0.149	Change the current working directory
`/clear`	optional name	0.105	Clear the terminal and start a fresh chat
`/compact`		0.11	Summarize the visible conversation to free context
`/copy`		0.105	Copy the latest completed output (also `Ctrl+O`)
`/debug-config`		0.97	Print configuration layers and requirements diagnostics
`/delete`		0.140	Permanently delete the current session and its child sessions
`/diff`		0.2	Show the Git diff, including untracked files
`/exit`		0.53	Exit the CLI (alias `/quit`)
`/experimental`		0.74	Toggle experimental features
`/export`	optional destination path	0.148	Export the conversation as Markdown
`/fast`		0.110	Toggle the Fast service tier when the active model offers one
`/feedback`		0.47	Send diagnostic logs to the Codex maintainers
`/fork`		0.81	Fork the current conversation into a new chat
`/goal`	`goal \| edit \| pause \| resume \| clear`	0.128	Set, edit, pause, or clear a task goal
`/hooks`		0.129	View and manage lifecycle hooks
`/ide`	optional text	0.129	Include open files, selection, and IDE context
`/import`		0.140	Import supported Claude Code or Cursor setup, projects, and chats
`/init`		0.14	Generate an AGENTS.md scaffold for project context
`/keymap`		0.128	Remap TUI keyboard shortcuts
`/logout`		0.15	Sign out of Codex
`/mcp`	`verbose`	0.23	List configured MCP tools
`/memories`		0.121	Configure memory use and generation
`/mention`	path	0.21	Attach a file or folder to the conversation
`/model`	model	0.23	Choose the active model and, when available, reasoning effort
`/new`	optional name	0.2	Start a new chat in the same CLI session
`/permissions`		0.89	Set what Codex can do without asking first
`/personality`		0.92	Choose a communication style for responses
`/pets`		0.131	Choose or hide a terminal pet (alias `/pet`)
`/plan`	optional prompt	0.93	Switch to plan mode
`/plugins`		0.117	Browse installed and discoverable plugins
`/ps`		0.76	Show background terminals and their recent output
`/pwd`		0.149	Show the current working directory (alias `/cwd`)
`/raw`	`on \| off`	0.129	Toggle raw scrollback mode
`/rename`	optional name	0.93	Rename the current chat
`/resume`		0.65	Resume a saved session from the session picker
`/review`		0.39	Ask Codex to review the working tree
`/sandbox-add-read-dir`	absolute path	0.102	Grant sandbox read access to a directory (Windows only)
`/setup-default-sandbox`		0.100	Set up the elevated default sandbox (Windows only)
`/side`	optional text	0.122	Start an ephemeral side conversation in a temporary fork (alias `/btw`)
`/skills`		0.65	Browse and use skills
`/status`		0.14	Show the model, approval policy, writable roots, and token usage
`/statusline`		0.99	Configure TUI status-line fields
`/stop`		0.115	Stop all background terminals (alias `/clean`)
`/subagents`		0.115	Switch between this session's subagents
`/theme`		0.105	Choose a syntax-highlighting theme
`/title`		0.117	Configure terminal-title fields
`/usage`	`daily \| weekly \| cumulative`	0.140	View account token usage or request a rate-limit reset
`/vim`		0.129	Toggle Vim mode for the composer

Keyboard Shortcuts: CLI (TUI)

These shortcuts work in the interactive terminal interface (started with codex). You can remap them with /keymap.

ShortcutCtrl+C

DescriptionCancels the current execution

ContextWhile the agent is working

ShortcutCtrl+D

DescriptionCloses the CLI

ContextWhen the input buffer is empty

ShortcutCtrl+G

DescriptionOpens external editor (VISUAL or EDITOR)

ContextFor long prompts

ShortcutCtrl+L

DescriptionClears the screen (without starting a new chat)

ContextWhen the terminal gets too cluttered

ShortcutCtrl+O

DescriptionCopies the last response to the clipboard

ContextAfter a response

ShortcutCtrl+R

DescriptionReverse search through prompt history

ContextIn the composer

ShortcutAlt+,

DescriptionLowers the reasoning depth

ContextDuring the session

ShortcutAlt+.

DescriptionRaises the reasoning depth

ContextDuring the session

ShortcutUp / Down

DescriptionNavigates the draft history in the composer

ContextIn the input field

ShortcutTab

DescriptionQueues follow-up text, slash commands, or shell commands

ContextWhile the agent is working

ShortcutEsc + Esc

DescriptionEdits the previous user message

ContextIn the composer

Shortcut@

DescriptionFuzzy file search for attaching files

ContextIn the input field

Shortcut!

DescriptionRuns a shell command directly

ContextAt the start of the input

Shortcut	Description	Context
`Ctrl+C`	Cancels the current execution	While the agent is working
`Ctrl+D`	Closes the CLI	When the input buffer is empty
`Ctrl+G`	Opens external editor (VISUAL or EDITOR)	For long prompts
`Ctrl+L`	Clears the screen (without starting a new chat)	When the terminal gets too cluttered
`Ctrl+O`	Copies the last response to the clipboard	After a response
`Ctrl+R`	Reverse search through prompt history	In the composer
`Alt+,`	Lowers the reasoning depth	During the session
`Alt+.`	Raises the reasoning depth	During the session
`Up / Down`	Navigates the draft history in the composer	In the input field
`Tab`	Queues follow-up text, slash commands, or shell commands	While the agent is working
`Esc + Esc`	Edits the previous user message	In the composer
`@`	Fuzzy file search for attaching files	In the input field
`!`	Runs a shell command directly	At the start of the input

Keyboard Shortcuts: Codex App

The desktop app (started with codex app) has its own shortcuts that follow common IDE conventions. On Windows, replace Cmd with Ctrl.

ShortcutCmd+Shift+P / Cmd+K

DescriptionOpens the command palette

ShortcutCmd+,

DescriptionOpens settings

ShortcutCmd+O

DescriptionOpens a folder

ShortcutCmd+N / Cmd+Shift+O

DescriptionNew thread

ShortcutCmd+F

DescriptionFind in thread

ShortcutCmd+B

DescriptionToggle sidebar

ShortcutCmd+Option+B

DescriptionToggle diff panel

ShortcutCmd+J

DescriptionToggle terminal

ShortcutCmd+Shift+[ / ]

DescriptionSwitch to previous / next thread

ShortcutCmd+[ / ]

DescriptionNavigate back / forward

ShortcutCmd++ / Cmd+-

DescriptionIncrease / decrease font size

ShortcutCtrl+L

DescriptionClear terminal

ShortcutCtrl+M

DescriptionStart dictation

Shortcut	Description
`Cmd+Shift+P / Cmd+K`	Opens the command palette
`Cmd+,`	Opens settings
`Cmd+O`	Opens a folder
`Cmd+N / Cmd+Shift+O`	New thread
`Cmd+F`	Find in thread
`Cmd+B`	Toggle sidebar
`Cmd+Option+B`	Toggle diff panel
`Cmd+J`	Toggle terminal
`Cmd+Shift+[ / ]`	Switch to previous / next thread
`Cmd+[ / ]`	Navigate back / forward
`Cmd++ / Cmd+-`	Increase / decrease font size
`Ctrl+L`	Clear terminal
`Ctrl+M`	Start dictation

Note

The app also supports deeplinks via the codex:// scheme, for example codex://settings for settings or codex://new?prompt=your+prompt for a new thread with a prompt.

Configuration (config.toml)

Codex config lives at ~/.codex/config.toml. You can set defaults and define named profiles.

Settingmodel

DescriptionDefault model for all sessions

Possible values"gpt-5.6-sol", "gpt-5.6-terra", or "gpt-5.6-luna", depending on your access

Settingmodel_reasoning_effort

DescriptionReasoning depth for complex tasks

Possible values"xhigh", "high", "medium", "low"

Settingpersonality

DescriptionCommunication style of the agent

Possible values"pragmatic", "friendly", "none"

Settingweb_search

DescriptionWeb search mode

Possible values"cached" (default), "live", "disabled"

Setting	Description	Possible values
`model`	Default model for all sessions	`"gpt-5.6-sol"`, `"gpt-5.6-terra"`, or `"gpt-5.6-luna"`, depending on your access
`model_reasoning_effort`	Reasoning depth for complex tasks	`"xhigh"`, `"high"`, `"medium"`, `"low"`
`personality`	Communication style of the agent	`"pragmatic"`, `"friendly"`, `"none"`
`web_search`	Web search mode	`"cached"` (default), `"live"`, `"disabled"`

# ~/.codex/config.toml

# Default settings
model = "gpt-5.6-terra"
model_reasoning_effort = "high"

# Profile for quick tasks
[profiles.quick]
model = "gpt-5.6-luna"
model_reasoning_effort = "low"

# Profile for thorough work
[profiles.thorough]
model = "gpt-5.6-sol"
model_reasoning_effort = "xhigh"

# Project trust level
[projects."/path/to/project"]
trust_level = "trusted"

# Override a single value
codex exec -s workspace-write -c model='"gpt-5.6-terra"' "Task"

# Set sandbox permissions
codex exec -s workspace-write \
  -c 'sandbox_permissions=["disk-full-read-access"]' "Task"

# Load a profile with -p
codex exec -s workspace-write -p quick "Quick question"

Feature Flags

Feature flags control both experimental and stable features. Changes via enable and disable are written permanently to config.toml. Per-run toggles with --enable and --disable only apply to the current run.

# List all feature flags with status and maturity
codex features list

# Permanently enable / disable a feature
codex features enable search_tool
codex features disable shell_snapshot

# Enable for this run only (not persistent)
codex exec -s workspace-write --enable search_tool \
  --disable shell_snapshot "Task"

Global Flags

These flags are available on almost every Codex command:

Flag--config, -c

DescriptionOverrides config.toml values. Dotted paths for nesting. Values are parsed as TOML.

Example-c model_reasoning_effort='"high"'

Flag--enable

DescriptionEnables a feature flag for this run (repeatable)

Examplecodex --enable search_tool

Flag--disable

DescriptionDisables a feature flag for this run (repeatable)

Examplecodex --disable search_tool

Flag--model, -m

DescriptionChooses a model for the current run

Examplecodex -m gpt-5.6-terra

Flag--oss / --local-provider

DescriptionUses a local open-source model and chooses LM Studio or Ollama when needed

Examplecodex --oss --local-provider ollama

Flag--remote

DescriptionConnects the TUI, resume, fork, and session archive actions to an app server over WebSocket or a Unix socket

Examplecodex --remote ws://127.0.0.1:4500

Flag--remote-auth-token-env

DescriptionReads a bearer token from an environment variable for --remote

Example--remote-auth-token-env CODEX_REMOTE_TOKEN

Flag--sandbox, -s

DescriptionChooses read-only, workspace-write, or danger-full-access

Example-s workspace-write

Flag--ask-for-approval, -a

DescriptionSets the approval policy to on-request or never

Examplecodex -a on-request

Flag--search

DescriptionSwitches from the default cached search to live web search

Examplecodex --search "Check the current documentation"

Flag--no-alt-screen

DescriptionRuns the TUI inline and preserves terminal scrollback

Examplecodex --no-alt-screen

Flag--strict-config

DescriptionFails on unrecognized config.toml fields

Examplecodex --strict-config

Flag--dangerously-bypass-approvals-and-sandbox, --yolo

DescriptionBypasses approvals and the sandbox. Use only inside an externally hardened environment.

Examplecodex --yolo "..."

Flag--dangerously-bypass-hook-trust

DescriptionRuns enabled hooks without persisted trust. Use only for already vetted automation.

Examplecodex --dangerously-bypass-hook-trust "..."

Flag--help, -h

DescriptionShows help

Examplecodex --help

Flag--version, -V

DescriptionShows the version number

Examplecodex --version

Flag	Description	Example
`--config, -c`	Overrides config.toml values. Dotted paths for nesting. Values are parsed as TOML.	`-c model_reasoning_effort='"high"'`
`--enable`	Enables a feature flag for this run (repeatable)	`codex --enable search_tool`
`--disable`	Disables a feature flag for this run (repeatable)	`codex --disable search_tool`
`--model, -m`	Chooses a model for the current run	`codex -m gpt-5.6-terra`
`--oss / --local-provider`	Uses a local open-source model and chooses LM Studio or Ollama when needed	`codex --oss --local-provider ollama`
`--remote`	Connects the TUI, resume, fork, and session archive actions to an app server over WebSocket or a Unix socket	`codex --remote ws://127.0.0.1:4500`
`--remote-auth-token-env`	Reads a bearer token from an environment variable for --remote	`--remote-auth-token-env CODEX_REMOTE_TOKEN`
`--sandbox, -s`	Chooses read-only, workspace-write, or danger-full-access	`-s workspace-write`
`--ask-for-approval, -a`	Sets the approval policy to on-request or never	`codex -a on-request`
`--search`	Switches from the default cached search to live web search	`codex --search "Check the current documentation"`
`--no-alt-screen`	Runs the TUI inline and preserves terminal scrollback	`codex --no-alt-screen`
`--strict-config`	Fails on unrecognized config.toml fields	`codex --strict-config`
`--dangerously-bypass-approvals-and-sandbox, --yolo`	Bypasses approvals and the sandbox. Use only inside an externally hardened environment.	`codex --yolo "..."`
`--dangerously-bypass-hook-trust`	Runs enabled hooks without persisted trust. Use only for already vetted automation.	`codex --dangerously-bypass-hook-trust "..."`
`--help, -h`	Shows help	`codex --help`
`--version, -V`	Shows the version number	`codex --version`

Troubleshooting

ProblemAuthentication fails

Likely causeStale token or wrong API key

SolutionRun codex logout, then codex login again

ProblemCodex hangs on codex exec

Likely causeThe approval policy requires confirmation in an unattended environment

SolutionFor controlled automation, set -s workspace-write and deliberately use -a never

ProblemCommand blocked in sandbox

Likely causeNetwork access or write access outside the working directory

SolutionFirst consider --add-dir for additional write paths. Use danger-full-access deliberately

ProblemMCP server doesn't connect

Likely causeMissing dependencies or wrong path

SolutionCheck codex mcp get server-name, then remove and add again

ProblemSession won't resume

Likely causeSession was started with --ephemeral

SolutionRestart without --ephemeral so sessions are saved

ProblemCloud task shows no diff

Likely causeTask is still running or has failed

SolutionCheck codex cloud status TASK_ID, then try again

ProblemCodex no longer starts after an update

Likely causeStale or unrecognized fields in config.toml

SolutionRun codex --strict-config and codex doctor --summary

Problem	Likely cause	Solution
Authentication fails	Stale token or wrong API key	Run codex logout, then codex login again
Codex hangs on codex exec	The approval policy requires confirmation in an unattended environment	For controlled automation, set -s workspace-write and deliberately use -a never
Command blocked in sandbox	Network access or write access outside the working directory	First consider --add-dir for additional write paths. Use danger-full-access deliberately
MCP server doesn't connect	Missing dependencies or wrong path	Check codex mcp get server-name, then remove and add again
Session won't resume	Session was started with --ephemeral	Restart without --ephemeral so sessions are saved
Cloud task shows no diff	Task is still running or has failed	Check codex cloud status TASK_ID, then try again
Codex no longer starts after an update	Stale or unrecognized fields in config.toml	Run codex --strict-config and codex doctor --summary

# Diagnose the config layers
# (in the interactive TUI)
/debug-config

# Show available models as JSON
codex debug models

# Show only the bundled model catalog (no API refresh)
codex debug models --bundled

# Validate exec policy rules (before saving)
codex execpolicy check --rules rules.toml -- npm test

# Log sandbox denials (debugging)
codex sandbox macos --log-denials -- ./build.sh

Codex Commands: The Complete Reference

Installing and Starting Codex

CLI Commands (Overview)

codex exec: Flags for Non-Interactive Execution

Common Patterns

Code Review

Session Management

Codex Cloud

App Server and Remote Control

Sandbox Modes

Approval Policies

MCP Servers (Model Context Protocol)

Slash Commands (CLI and App)

Keyboard Shortcuts: CLI (TUI)

Keyboard Shortcuts: Codex App

Configuration (config.toml)

Feature Flags

Global Flags

Troubleshooting

FAQ

Frequently Asked Questions

Finn Hillebrandt

Similar Articles

Claude Code Commands (100+): The Reference

Claude Code vs. Codex: My In-Depth Test

Claude Code Alternatives 2026: 12 AI Coding Tools Compared

How to Use Claude Code for Free (And What the Limits Are)

Claude Code Pricing: How Much Does Claude Code Really Cost?

OpenAI Codex Statistics 2026: Key Numbers, Data & Facts

Installing and Starting Codex

CLI Commands (Overview)

codex exec: Flags for Non-Interactive Execution

Common Patterns

Code Review

Session Management

Codex Cloud

App Server and Remote Control

Sandbox Modes

Approval Policies

MCP Servers (Model Context Protocol)

Slash Commands (CLI and App)

Keyboard Shortcuts: CLI (TUI)

Keyboard Shortcuts: Codex App

Configuration (config.toml)

Feature Flags

Global Flags

Troubleshooting

FAQ

Frequently Asked Questions

Is Codex CLI free?

What's the difference between Codex CLI and the Codex App?

Which model should I use with Codex?

What's the difference between codex exec and interactive codex?

How do I resume a previous session?

What does the sandbox actually do?

Can I use Codex CLI in my CI/CD pipeline?

How does Codex differ from Claude Code?

Finn Hillebrandt

Similar Articles

Claude Code Commands (100+): The Reference

Claude Code vs. Codex: My In-Depth Test

Claude Code Alternatives 2026: 12 AI Coding Tools Compared

How to Use Claude Code for Free (And What the Limits Are)

Claude Code Pricing: How Much Does Claude Code Really Cost?

OpenAI Codex Statistics 2026: Key Numbers, Data & Facts