# Codex OpenAI's agent for software work: understand, change, and test code. Available in the desktop app, terminal (CLI), editor, and cloud. Canonical profile: https://agenten-kompass.mmeierhoff.chatgpt.site/en/agents/codex/ Editor: [Michael Meierhoff](https://agenten-kompass.mmeierhoff.chatgpt.site/en/about/) Sources reviewed: 2026-10-09 Basis: provider documentation. Examples are editorial suggestions, not hands-on product tests. ## Overview Codex is OpenAI's agent for software work. You can use it in the desktop app, in the terminal through the Codex CLI, in the code editor, or in the cloud. The CLI provides command-line access. dots can delegate development tasks to Codex. - Provider: OpenAI - Product family: ChatGPT and Codex - Profile type: Coding agent - Environment: App, CLI, editor, and cloud - Connections: Repositories and development tools - Setup: Provide project rules and the task - Pricing model: Free: USD 0; Plus: USD 20/month; Pro: USD 100, 200 or 500/month ## Operation & oversight Operational details for this profile have not yet been researched. ## Provider OpenAI develops GPT models, ChatGPT and Codex. The operating company is a public benefit corporation controlled by the nonprofit OpenAI Foundation. The linked repository contains Codex CLI. - Operator: OpenAI Group PBC - Organization: Company controlled by the OpenAI Foundation - Website: https://openai.com/ - Reviewed: 2026-10-09 - Repository: https://github.com/openai/codex - GitHub-Stars: 128271 (2026-10-09) - License: Apache-2.0 - Provider source: https://openai.com/our-structure/ - Provider source: https://api.github.com/repos/openai/codex ## Prices and included usage Pricing checked: 2026-10-09 Usage through a ChatGPT plan. Work and Codex share included allowances. ### Free USD 0 Limited Codex usage and Work on desktop. Price source: https://chatgpt.com/pricing/ ### Plus USD 20 per month, billed monthly More Work and Codex usage; API consumption is billed separately. Price source: https://help.openai.com/en/articles/6950777-what-is-chatgpt-plus ### Pro USD 100 / 200 / 500 per month Three usage tiers; Ultrafast is included in Pro 500. Price source: https://help.openai.com/en/articles/9793128-about-chatgpt-pro-tiers ### Business Standard USD 25 per seat/month; USD 20 billed annually ChatGPT, Work and Codex; at least two Standard or Premium seats in total. Price source: https://help.openai.com/en/articles/8792828-chatgpt-business-overview The listed USD prices refer to web subscriptions. Business offers additional workspace credits. Pricing details: https://chatgpt.com/pricing/ ## Key features ### Inspect and modify code Codex handles development tasks based on a project, can prepare changes, and run the associated checks. Source: https://openai.com/codex/ ### CLI, IDE, and cloud You can use Codex in the terminal, alongside code in the editor, and in configured cloud environments. The access method affects the workflow. Source: https://learn.chatgpt.com/docs/app ### Parallel work in worktrees Independent tasks can use separate Git working copies. Changes and files remain separate for each worktree. Source: https://learn.chatgpt.com/docs/environments/git-worktrees ### Move tasks between workspaces Handoff transfers a task between a local checkout and a managed worktree. Git state and ignored files must be considered. Source: https://learn.chatgpt.com/docs/environments/git-worktrees ### Skills for project workflows Skills bundle instructions and resources for recurring work. They can describe project routines such as reviews or documentation. Source: https://learn.chatgpt.com/docs/build-skills ### Scheduled development tasks You can schedule tasks in the desktop app. Git projects can use dedicated working copies for this. The computer and app must be running for local work. Source: https://learn.chatgpt.com/docs/automations ### Project rules with AGENTS.md Global and project-specific instructions define working methods, conventions, and checks for development tasks. Source: https://learn.chatgpt.com/docs/agent-configuration/agents-md ### Specialized subagents Independent subtasks can be assigned to parallel agents. Local Codex clients support custom agent configurations; additional agents consume additional usage. Source: https://learn.chatgpt.com/docs/agent-configuration/subagents ### Connect MCP tools Local Codex clients connect to local or remote MCP servers. App, CLI, and IDE share the configuration of the same host. Source: https://learn.chatgpt.com/docs/extend/mcp ### Hooks for your own checks Trusted hooks run scripts or MCP tools on agent events, for example for validation, logging, or policy enforcement. Source: https://learn.chatgpt.com/docs/hooks ### Ultrafast with GPT-6.1 Sol Ultrafast speeds up token generation with GPT-6.1 Sol. Access is limited to Pro 500 and eligible Enterprise and Edu plans; Enterprise requires approval. Source: https://learn.chatgpt.com/docs/whats-new/october-5-9-2026 ### Review code and pull requests Inspect diffs, comments and checks together. GitHub reviews are generally available; GitLab support is in preview. Source: https://learn.chatgpt.com/docs/code-review ### Continue on remote computers Work on connected hosts or SSH projects using the host’s tools and permissions. Source: https://learn.chatgpt.com/docs/remote-connections ## Requirements and limits ### Access to files and the network Requirement: The environment and permission profile determine which files Codex can read or change and which services it can access. Source: https://learn.chatgpt.com/docs/permissions ### Local schedules require the app to be running Requirement: For scheduled work in a local project, the computer and desktop app must be running and the project available. Source: https://learn.chatgpt.com/docs/automations ### Schedules are managed in the app or on the web Limitation: The CLI and editor extension do not have their own Scheduled management. You can prepare tasks there; they are configured in the app or on the web. Source: https://learn.chatgpt.com/docs/automations ## Example workflows ### Add a small feature - Your input: Repository, acceptance criteria, and existing project rules. - Possible result: A verifiable diff with suitable tests and notes on remaining questions. - What to check: Test the feature in the actual workflow and review the code. ### Prepare two independent changes - Your input: Two clearly separated tasks in the same Git project. - Possible result: Separate worktree changes for review and later integration. - What to check: Check interactions and merge conflicts before adoption. ## Context Local automations require a running computer and app. Schedules are managed in the app or on the web; GitLab code review is in preview. This profile describes development work. App features such as document views or general Work tasks are covered in the separate desktop app profile. ## Sources - https://openai.com/codex/ - https://learn.chatgpt.com/docs/app - https://learn.chatgpt.com/docs/environments/git-worktrees - https://learn.chatgpt.com/docs/build-skills - https://learn.chatgpt.com/docs/agent-configuration/agents-md - https://learn.chatgpt.com/docs/agent-configuration/subagents - https://learn.chatgpt.com/docs/extend/mcp - https://learn.chatgpt.com/docs/hooks - https://learn.chatgpt.com/docs/automations - https://learn.chatgpt.com/docs/permissions - https://learn.chatgpt.com/docs/whats-new/october-5-9-2026 - https://learn.chatgpt.com/docs/code-review - https://learn.chatgpt.com/docs/remote-connections [Sources and method](https://agenten-kompass.mmeierhoff.chatgpt.site/en/sources/)