### Install and Start WSL

Source: https://learn.chatgpt.com/docs/windows/wsl

Commands to install the default Linux distribution and initiate a shell session.

```powershell
# Install default Linux distribution (like Ubuntu)
wsl --install

# Start a shell inside Windows Subsystem for Linux
wsl
```

--------------------------------

### Setup Windows sandbox with windowsSandbox/setupStart

Source: https://learn.chatgpt.com/docs/app-server

Triggers asynchronous Windows sandbox setup. Includes the request and the subsequent completion notification.

```json
{ "method": "windowsSandbox/setupStart", "id": 53, "params": { "mode": "elevated" } }
{ "id": 53, "result": { "started": true } }
```

```json
{
  "method": "windowsSandbox/setupCompleted",
  "params": { "mode": "elevated", "success": true, "error": null }
}
```

--------------------------------

### windowsSandbox/setupStart

Source: https://learn.chatgpt.com/docs/app-server

Triggers the Windows sandbox setup process asynchronously.

```APIDOC
## windowsSandbox/setupStart

### Description
Triggers sandbox setup asynchronously for custom Windows clients.

### Parameters
- **mode** (string) - Required - The setup mode, either 'elevated' or 'unelevated'.
```

--------------------------------

### Install project dependencies

Source: https://learn.chatgpt.com/docs/mcp-server

Sets up a Python virtual environment and installs the required OpenAI Agents SDK packages.

```bash
python -m venv .venv
source .venv/bin/activate
pip install --upgrade openai openai-agents python-dotenv
```

--------------------------------

### Start development server

Source: https://learn.chatgpt.com/docs/prompting

Run the Vite development server.

```bash
npm run dev
```

--------------------------------

### Run unattended installer

Source: https://learn.chatgpt.com/docs/config-file/environment-variables

Use these commands to execute the installer without interactive prompts.

```bash
curl -fsSL https://chatgpt.com/codex/install.sh | CODEX_NON_INTERACTIVE=1 sh
```

```powershell
$env:CODEX_NON_INTERACTIVE=1; irm https://chatgpt.com/codex/install.ps1 | iex
```

--------------------------------

### Configure custom setup script

Source: https://learn.chatgpt.com/docs/environments/cloud-environment

Use a custom Bash script to install specific tools or dependencies that are not handled by automatic package manager detection.

```bash
# Install type checker
pip install pyright

# Install dependencies
poetry install --with test
pnpm install
```

--------------------------------

### plugin/install

Source: https://learn.chatgpt.com/docs/app-server

Install a plugin from a marketplace.

```APIDOC
## plugin/install

### Description
Install a plugin from a marketplace path or remote marketplace name. Note: This method is currently under development and should not be used in production clients.
```

--------------------------------

### Install ChatGPT via Winget

Source: https://learn.chatgpt.com/docs/windows/windows-app

Use the Windows Package Manager to install the ChatGPT desktop application from the Microsoft Store.

```powershell
winget install Codex -s msstore
```

--------------------------------

### Install Developer Tools via Winget

Source: https://learn.chatgpt.com/docs/windows/windows-app

Use these commands in the integrated terminal to install Git, Node.js, Python, .NET SDK, and GitHub CLI.

```powershell
winget install --id Git.Git
winget install --id OpenJS.NodeJS.LTS
winget install --id Python.Python.3.14
winget install --id Microsoft.DotNet.SDK.10
winget install --id GitHub.cli
```

--------------------------------

### Install Codex SDK for Python

Source: https://learn.chatgpt.com/docs/codex-sdk

Install the Python SDK via pip. Use --pre for prerelease builds if necessary.

```bash
pip install openai-codex
```

--------------------------------

### Configure Sandbox Policies

Source: https://learn.chatgpt.com/docs/app-server

Examples of read-only and workspace-write sandbox policy configurations.

```json
{ "type": "readOnly", "access": { "type": "fullAccess" } }
```

```json
{
  "type": "workspaceWrite",
  "writableRoots": ["/Users/me/project"],
  "readOnlyAccess": {
    "type": "restricted",
    "includePlatformDefaults": true,
    "readableRoots": ["/Users/me/shared-read-only"]
  },
  "networkAccess": false
}
```

--------------------------------

### Implement Node.js Client Integration

Source: https://learn.chatgpt.com/docs/app-server

Example of spawning the app-server process and communicating via stdio in Node.js.

```ts



const proc = spawn("codex", ["app-server"], {
  stdio: ["pipe", "pipe", "inherit"],
});
const rl = readline.createInterface({ input: proc.stdout });

const send = (message: unknown) => {
  proc.stdin.write(`${JSON.stringify(message)}\n`);
};

let threadId: string | null = null;

rl.on("line", (line) => {
  const msg = JSON.parse(line) as any;
  console.log("server:", msg);

  if (msg.id === 1 && msg.result?.thread?.id && !threadId) {
    threadId = msg.result.thread.id;
    send({
      method: "turn/start",
      id: 2,
      params: {
        threadId,
        input: [{ type: "text", text: "Summarize this repo." }],
      },
    });
  }
});

send({
  method: "initialize",
  id: 0,
  params: {
    clientInfo: {
      name: "my_product",
      title: "My Product",
      version: "0.1.0",
    },
  },
});
send({ method: "initialized", params: {} });
send({ method: "thread/start", id: 1, params: { model: "gpt-5.4" } });
```

--------------------------------

### Launch Codex App Server with stdio

Source: https://learn.chatgpt.com/docs/developer-commands?surface=app

Starts the server using the default JSONL-over-stdio transport.

```bash
codex app-server --listen stdio://
```

```bash
codex app-server --stdio
```

--------------------------------

### Start WebSocket Listener

Source: https://learn.chatgpt.com/docs/app-server

Initializes the app-server to listen for incoming connections on a specified WebSocket address.

```bash
codex app-server --listen ws://127.0.0.1:4500
```

--------------------------------

### GET /readyz

Source: https://learn.chatgpt.com/docs/app-server

Checks if the server is ready to accept new connections.

```APIDOC
## GET /readyz

### Description
Returns 200 OK once the listener accepts new connections.

### Method
GET

### Endpoint
/readyz

### Response
#### Success Response (200)
- **Status** (string) - OK
```

--------------------------------

### codex://plugins/install/<plugin-name>

Source: https://learn.chatgpt.com/docs/reference/commands

Opens the install flow for a plugin from a known marketplace.

```APIDOC
## codex://plugins/install/<plugin-name>

### Description
Opens the plugin detail or install flow for a plugin from a marketplace that Codex recognizes.

### Parameters
#### Path Parameters
- **plugin-name** (string) - Required - The name of the plugin to install.

#### Query Parameters
- **marketplace** (string) - Required - Identifies the marketplace. Use 'openai-curated' for OpenAI-curated plugins.
```

--------------------------------

### Example configuration for an MCP server

Source: https://learn.chatgpt.com/docs/extend/mcp

Demonstrates a basic STDIO server configuration using npx and custom environment variables.

```toml
[mcp_servers.context7]
command = "npx"
args = ["-y", "@upstash/context7-mcp"]
env_vars = ["LOCAL_TOKEN"]

[mcp_servers.context7.env]
MY_ENV_VAR = "MY_ENV_VALUE"
```

--------------------------------

### Configure TypeScript project setup

Source: https://learn.chatgpt.com/docs/environments/local-environment

Run these commands automatically when Codex creates a new worktree to ensure dependencies are installed and the project is built.

```bash
npm install
npm run build
```

--------------------------------

### Codex Configuration Template

Source: https://learn.chatgpt.com/docs/config-file/config-sample

Use this TOML configuration as a starting point for ~/.codex/config.toml or project-scoped configurations. Root keys must be defined before tables, and optional settings are provided as commented-out examples.

```toml
# Codex example configuration (config.toml)
#
# This file lists the main keys Codex reads from config.toml, along with default
# behaviors, recommended examples, and concise explanations. Adjust as needed.
#
# Notes
# - Root keys must appear before tables in TOML.
# - Optional keys that default to "unset" are shown commented out with notes.
# - MCP servers, profile files, and model providers are examples; remove or edit.

################################################################################

# Core Model Selection

################################################################################

# Primary model used by Codex. Recommended example for most users: "gpt-5.6".

model = "gpt-5.6"

# Communication style for supported models. Allowed values: none | friendly | pragmatic

# personality = "pragmatic"

# Optional model override for /review. Default: unset (uses current session model).

# review_model = "gpt-5.6"

# Provider id selected from [model_providers]. Default: "openai".

model_provider = "openai"

# Default OSS provider for --oss sessions. When unset, Codex prompts. Default: unset.

# oss_provider = "ollama"

# Preferred service tier. Built-in examples: fast | flex; model catalogs can add more.

# service_tier = "flex"

# Optional manual model metadata. When unset, Codex uses model or preset defaults.

# model_context_window = 128000 # tokens; default: auto for model

# model_auto_compact_token_limit = 64000 # tokens; unset uses model defaults

# model_auto_compact_token_limit_scope = "total" # total | body_after_prefix; default: total

# tool_output_token_limit = 12000 # tokens stored per tool output

# model_catalog_json = "/absolute/path/to/models.json" # optional startup-only model catalog override

# background_terminal_max_timeout = 300000 # ms; max empty write_stdin poll window (default 5m)

# log_dir = "/absolute/path/to/codex-logs" # log directory; setting explicitly enables codex-tui.log; default: "$CODEX_HOME/log"

# sqlite_home = "/absolute/path/to/codex-state" # optional SQLite-backed runtime state directory

################################################################################

# Reasoning & Verbosity (Responses API capable models)

################################################################################

# Reasoning effort: minimal | low | medium | high | xhigh

# model_reasoning_effort = "medium"

# Optional override used when Codex runs in plan mode: none | minimal | low | medium | high | xhigh

# plan_mode_reasoning_effort = "high"

# Reasoning summary: auto | concise | detailed | none

# model_reasoning_summary = "auto"

# Text verbosity for GPT-5 family (Responses API): low | medium | high

# model_verbosity = "medium"

# Force enable or disable reasoning summaries for current model.

# model_supports_reasoning_summaries = true

################################################################################

# Instruction Overrides

################################################################################

# Additional user instructions are injected before AGENTS.md. Default: unset.

# developer_instructions = ""

# Inline override for the history compaction prompt. Default: unset.

# compact_prompt = ""

# Override built-in base instructions with a file path. Default: unset.

# model_instructions_file = "/absolute/or/relative/path/to/instructions.txt"

# Load the compact prompt override from a file. Default: unset.

# experimental_compact_prompt_file = "/absolute/or/relative/path/to/compact_prompt.txt"

################################################################################

# Notifications

################################################################################

# External notifier program (argv array). When unset: disabled.

# notify = ["notify-send", "Codex"]

################################################################################

# Approval & Sandbox

################################################################################

# When to ask for command approval:
```

--------------------------------

### Install bubblewrap on Linux

Source: https://learn.chatgpt.com/docs/sandboxing

Install the bubblewrap package using the system's package manager.

```bash
sudo apt install bubblewrap
```

```bash
sudo dnf install bubblewrap
```

--------------------------------

### Install local plugin to repository

Source: https://learn.chatgpt.com/docs/build-plugins

Commands to create the plugin directory and copy the plugin files into the repository root.

```bash
mkdir -p ./plugins
cp -R /absolute/path/to/my-plugin ./plugins/my-plugin
```

--------------------------------

### Create a plugin directory

Source: https://learn.chatgpt.com/docs/build-plugins

Initialize the folder structure for a new plugin.

```bash
mkdir -p my-first-plugin/.codex-plugin
```

--------------------------------

### Install Codex SDK for TypeScript

Source: https://learn.chatgpt.com/docs/codex-sdk

Use npm to install the required package for the TypeScript SDK.

```bash
npm install @openai/codex-sdk
```

--------------------------------

### Prompt injection example request

Source: https://learn.chatgpt.com/docs/cloud/internet-access

Example of a user prompt that directs an agent to a specific GitHub issue.

```text
Fix this issue: https://github.com/org/repo/issues/123
```

--------------------------------

### Start Dev Container via CLI

Source: https://learn.chatgpt.com/docs/agent-approvals-security

Use the devcontainer CLI to initialize the environment using the secure configuration file.

```bash
devcontainer up --workspace-folder . --config .devcontainer/devcontainer.secure.json
```

--------------------------------

### Install and Run Codex in WSL

Source: https://learn.chatgpt.com/docs/windows/wsl

Download and execute the Codex CLI installation script within the Linux environment.

```bash
# Install and run Codex in WSL
curl -fsSL https://chatgpt.com/codex/install.sh | sh
codex
```

--------------------------------

### Initialize Project Directory

Source: https://learn.chatgpt.com/docs/windows/wsl

Create a workspace directory in the Linux home path to ensure optimal I/O performance.

```bash
mkdir -p ~/code && cd ~/code
git clone https://github.com/your/repo.git
cd repo
```

--------------------------------

### Explain Codebase via CLI

Source: https://learn.chatgpt.com/docs/prompting

Use file references with @ to provide context for protocol or schema analysis.

```text
I need to understand the protocol used by this service. Read @foo.ts @schema.ts and explain the schema and request/response flow. Focus on required vs optional fields and backward compatibility rules.
```

--------------------------------

### Configure MCP Servers

Source: https://learn.chatgpt.com/docs/config-file/config-sample

Examples for setting up MCP servers using either STDIO or HTTP transport protocols.

```toml
[mcp_servers.docs]
enabled = true # optional; default true
required = true # optional; fail startup/resume if this server cannot initialize
command = "docs-server" # required
args = ["--port", "4000"] # optional
env = { "API_KEY" = "value" } # optional key/value pairs copied as-is
env_vars = ["ANOTHER_SECRET"] # optional: forward local parent env vars
env_vars = ["LOCAL_TOKEN", { name = "REMOTE_TOKEN", source = "remote" }]
cwd = "/path/to/server" # optional working directory override
experimental_environment = "remote" # experimental: run stdio via a remote executor
startup_timeout_sec = 10.0 # optional; default 10.0 seconds
# startup_timeout_ms = 10000 # optional alias for startup timeout (milliseconds)
tool_timeout_sec = 60.0 # optional; default 60.0 seconds
enabled_tools = ["search", "summarize"] # optional allow-list
disabled_tools = ["slow-tool"] # optional deny-list (applied after allow-list)
scopes = ["read:docs"] # optional OAuth scopes
oauth_resource = "https://docs.example.com/" # optional OAuth resource
```

```toml
[mcp_servers.github]
enabled = true # optional; default true
required = true # optional; fail startup/resume if this server cannot initialize
url = "https://github-mcp.example.com/mcp" # required
bearer_token_env_var = "GITHUB_TOKEN" # optional; Authorization: Bearer <token>
http_headers = { "X-Example" = "value" } # optional static headers
env_http_headers = { "X-Auth" = "AUTH_ENV" } # optional headers populated from env vars
startup_timeout_sec = 10.0 # optional
tool_timeout_sec = 60.0 # optional
enabled_tools = ["list_issues"] # optional allow-list
disabled_tools = ["delete_issue"] # optional deny-list
scopes = ["repo"] # optional OAuth scopes
```

--------------------------------

### PowerShell Execution Policy Error Example

Source: https://learn.chatgpt.com/docs/windows/windows-app

Example of an error message encountered when PowerShell blocks script execution.

```text
npm.ps1 cannot be loaded because running scripts is disabled on this system.
```

--------------------------------

### Create a SKILL.md file

Source: https://learn.chatgpt.com/docs/customization/overview

A sample SKILL.md file containing frontmatter metadata and instructional content for the agent.

```markdown
---
name: commit
description: Stage and commit changes in semantic groups. Use when the user wants to commit, organize commits, or clean up a branch before pushing.
---

1. Do not run `git add .`. Stage files in logical groups by purpose.
2. Group into separate commits: feat → test → docs → refactor → chore.
3. Write concise commit messages that match the change scope.
4. Keep each commit focused and reviewable.
```

--------------------------------

### Start a Turn with Skill Invocation

Source: https://learn.chatgpt.com/docs/app-server

Starts a turn that explicitly invokes a skill by providing the skill name and path.

```json
{ "method": "turn/start", "id": 33, "params": {
  "threadId": "thr_123",
  "input": [
    { "type": "text", "text": "$skill-creator Add a new skill for triaging flaky CI and include step-by-step usage." },
    { "type": "skill", "name": "skill-creator", "path": "/Users/me/.codex/skills/skill-creator/SKILL.md" }
  ]
} }
{ "id": 33, "result": { "turn": { "id": "turn_457", "status": "inProgress", "items": [], "error": null } } }
```

--------------------------------

### Launch with Experimental Features

Source: https://learn.chatgpt.com/docs/developer-commands?surface=app

Includes gated fields and methods when generating schemas for client bindings.

```bash
codex app-server --experimental
```

--------------------------------

### account/login/start (ChatGPT Device-Code Flow)

Source: https://learn.chatgpt.com/docs/app-server

Initiates a device-code login flow for ChatGPT.

```APIDOC
## account/login/start (ChatGPT Device-Code Flow)

### Description
Starts the device-code login flow, providing a verification URL and user code for the user to authenticate externally.

### Parameters
- **type** (string) - Required - Must be "chatgptDeviceCode".

### Request Example
{ "method": "account/login/start", "id": 4, "params": { "type": "chatgptDeviceCode" } }
```

--------------------------------

### Install local plugin to personal directory

Source: https://learn.chatgpt.com/docs/build-plugins

Commands to create the personal plugin directory and copy the plugin files into the user's home directory.

```bash
mkdir -p ~/.codex/plugins
cp -R /absolute/path/to/my-plugin ~/.codex/plugins/my-plugin
```

--------------------------------

### Configure Project Documentation and Root

Source: https://learn.chatgpt.com/docs/config-schema.json

Settings for project documentation fallback files and root directory detection.

```json
"project_doc_fallback_filenames": {
      "default": [],
      "description": "Ordered list of fallback filenames to look for when AGENTS.md is missing.",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "project_doc_max_bytes": {
      "default": 32768,
      "description": "Maximum number of bytes to include from an AGENTS.md project doc file.",
      "format": "uint",
      "minimum": 0.0,
      "type": "integer"
    },
    "project_root_markers": {
      "default": null,
      "description": "Markers used to detect the project root when searching parent directories for `.codex` folders. Defaults to [".git"] when unset.",
      "items": {
        "type": "string"
      },
      "type": "array"
    }
```

--------------------------------

### Install Visual Studio Build Tools via winget

Source: https://learn.chatgpt.com/docs/windows/windows-sandbox

Use this command to install the required C++ build tools if the IDE extension is unresponsive due to missing dependencies.

```powershell
winget install --id Microsoft.VisualStudio.2022.BuildTools -e
```

--------------------------------

### codex plugin remove

Source: https://learn.chatgpt.com/docs/developer-commands?surface=cli

Remove an installed plugin.

```APIDOC
## codex plugin remove <plugin[@marketplace]>

### Description
Remove an installed plugin from local config and cache.

### Parameters
- **plugin[@marketplace]** (string) - Required - The plugin identifier to remove.
- **--marketplace, -m** (string) - Optional - The name of the marketplace.
- **--json** (flag) - Optional - Enables automation-friendly output.
```

--------------------------------

### codex plugin list

Source: https://learn.chatgpt.com/docs/developer-commands?surface=cli

List installed plugins.

```APIDOC
## codex plugin list

### Description
List installed plugins. With --json, output has installed and available arrays; --available includes uninstalled marketplace plugins and requires --json.

### Parameters
- **--marketplace, -m** (string) - Optional - The name of the marketplace.
- **--available** (flag) - Optional - Includes uninstalled marketplace plugins (requires --json).
- **--json** (flag) - Optional - Enables automation-friendly output.
```

--------------------------------

### account/login/start (API Key)

Source: https://learn.chatgpt.com/docs/app-server

Initiates a login session using an API key.

```APIDOC
## account/login/start (API Key)

### Description
Logs the user in using a provided API key.

### Parameters
- **type** (string) - Required - Must be "apiKey".
- **apiKey** (string) - Required - The API key string.

### Request Example
{ "method": "account/login/start", "id": 2, "params": { "type": "apiKey", "apiKey": "sk-..." } }
```

--------------------------------

### thread/start

Source: https://learn.chatgpt.com/docs/app-server

Starts a fresh thread for a new conversation.

```APIDOC
## thread/start

### Description
Starts a fresh thread for a new conversation. Returns the thread details including ID and session ID.

### Parameters
- **model** (string) - Required - The model to use (e.g., "gpt-5.4")
- **cwd** (string) - Required - Current working directory
- **approvalPolicy** (string) - Optional - Approval policy setting
- **sandbox** (string) - Optional - Sandbox environment type
- **personality** (string) - Optional - Personality setting
- **serviceName** (string) - Optional - Integration service name for metrics
- **historyMode** (string) - Optional - Experimental: "legacy" or "paginated"
- **permissions** (string) - Optional - Beta: Named permission-profile ID
- **dynamicTools** (array) - Optional - Experimental: Tools to persist in thread metadata

### Request Example
{ "method": "thread/start", "id": 10, "params": { "model": "gpt-5.4", "cwd": "/Users/me/project", "approvalPolicy": "never", "sandbox": "workspaceWrite", "personality": "friendly", "serviceName": "my_app_server_client" } }
```

--------------------------------

### account/login/start (ChatGPT Browser Flow)

Source: https://learn.chatgpt.com/docs/app-server

Initiates a browser-based login flow for ChatGPT.

```APIDOC
## account/login/start (ChatGPT Browser Flow)

### Description
Starts the browser-based login flow, returning an authentication URL for the user to visit.

### Parameters
- **type** (string) - Required - Must be "chatgpt".
- **useHostedLoginSuccessPage** (boolean) - Optional - Whether to use the hosted success page.
- **appBrand** (string) - Optional - The brand identifier, defaults to "codex".

### Request Example
{ "method": "account/login/start", "id": 3, "params": { "type": "chatgpt", "useHostedLoginSuccessPage": true, "appBrand": "chatgpt" } }
```

--------------------------------

### GET /healthz

Source: https://learn.chatgpt.com/docs/app-server

Checks the health status of the server.

```APIDOC
## GET /healthz

### Description
Returns 200 OK when the request does not include an Origin header. Requests with an Origin header are rejected with 403 Forbidden.

### Method
GET

### Endpoint
/healthz

### Response
#### Success Response (200)
- **Status** (string) - OK

#### Error Response (403)
- **Status** (string) - Forbidden (returned if Origin header is present)
```

--------------------------------

### Create a skill directory

Source: https://learn.chatgpt.com/docs/build-plugins

Initialize the folder structure for a specific skill within a plugin.

```bash
mkdir -p my-first-plugin/skills/hello
```

--------------------------------

### codex plugin add

Source: https://learn.chatgpt.com/docs/developer-commands?surface=cli

Install a plugin from a configured marketplace.

```APIDOC
## codex plugin add <plugin[@marketplace]>

### Description
Install a plugin from a configured marketplace. Use --marketplace or -m when the plugin argument omits @marketplace.

### Parameters
- **plugin[@marketplace]** (string) - Required - The plugin identifier, optionally including the marketplace name.
- **--marketplace, -m** (string) - Optional - The name of the marketplace.
- **--json** (flag) - Optional - Enables automation-friendly output.
```

--------------------------------

### Coordinate a product launch plan

Source: https://learn.chatgpt.com/docs/prompting

Use this prompt to generate comprehensive project management documentation based on a product brief.

```text
Create a launch plan for the attached product brief. Include the timeline,
owners, dependencies, risks, announcement draft, customer FAQ, and a checklist
for launch day. Flag any missing decisions before producing the final files.
```

--------------------------------

### account/login/start

Source: https://learn.chatgpt.com/docs/app-server

Initiates a login session using externally managed ChatGPT tokens. Requires experimentalApi capability to be enabled.

```APIDOC
## account/login/start

### Description
Initiates a login session using externally managed ChatGPT tokens. Clients must set `capabilities.experimentalApi = true` during initialization.

### Request
```json
{
  "method": "account/login/start",
  "id": 7,
  "params": {
    "type": "chatgptAuthTokens",
    "accessToken": "<jwt>",
    "chatgptAccountId": "org-123",
    "chatgptPlanType": "business"
  }
}
```

### Response
```json
{ "id": 7, "result": { "type": "chatgptAuthTokens" } }
```
```

--------------------------------

### codex plugin marketplace add

Source: https://learn.chatgpt.com/docs/developer-commands?surface=cli

Install a plugin marketplace source.

```APIDOC
## codex plugin marketplace add <source>

### Description
Install a plugin marketplace from GitHub shorthand, a Git URL, an SSH URL, or a local marketplace root directory.

### Parameters
- **source** (string) - Required - The marketplace source location.
- **--ref** (string) - Optional - Pin a specific Git ref.
- **--sparse** (string) - Optional - Use a sparse checkout for Git-backed repositories (can be repeated).
- **--json** (flag) - Optional - Enables automation-friendly output.
```

--------------------------------

### Start CLI Session

Source: https://learn.chatgpt.com/docs/prompting

Initialize an interactive Codex session in the terminal.

```bash
codex
```

--------------------------------

### account/login/start

Source: https://learn.chatgpt.com/docs/app-server

Initiates a login process using various authentication modes.

```APIDOC
## account/login/start

### Description
Begin login using one of the supported modes: apiKey, chatgpt, chatgptDeviceCode, or chatgptAuthTokens.
```