Official Technical Resources: OpenAI (page 12)
Official Technical Resources · OpenAI: 258 entries in total; this page lists entries 166–180.
Model Context Protocol
Give Codex access to third-party tools and context
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Agent Skills · Agent Memory
Link last checked: 2026-09-24
Record & Replay
Show ChatGPT or Codex a workflow once and turn it into a reusable skill
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Agent Skills · Agent Memory
Link last checked: 2026-09-24
Feature Maturity
How to interpret feature maturity levels in ChatGPT releases
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Workflow Orchestration · AI Agent
Link last checked: 2026-09-24
Codex GitHub Action
Trigger Codex actions from GitHub Events
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Coding Tools · Model Deployment Options
Link last checked: 2026-09-24
Hooks
Run scripts or MCP tools during the Codex lifecycle
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Agent Skills · Agent Memory
Link last checked: 2026-09-24
Codex IDE extension
Use Codex beside your code and editor context.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Coding Tools · Model Deployment Options
Link last checked: 2026-09-24
Best practices
Getting started with Codex and proven practices for better results
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Workflow Orchestration · AI Agent
Link last checked: 2026-09-24
Long-running work
Keep multi-step work focused with clear outcomes and completion criteria
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Workflow Orchestration · AI Agent
Link last checked: 2026-09-24
Codex MCP server removal
Migrate from the removed Codex MCP server to the app server
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Coding Tools · Model Deployment Options
Link last checked: 2026-09-24
Model selection
Find the right model for your use case
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Model Selection and Cost · Major Model Families
Link last checked: 2026-09-24
Non-interactive mode
Use `codex exec` to run Codex in scripts and CI
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Coding Tools · Model Deployment Options
Link last checked: 2026-09-24
Permissions
Choose what ChatGPT can do on your computer and when it asks for approval
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Agent Identity, Authorization, and Secrets · AI Guardrails
Link last checked: 2026-09-24
Sandbox
How sandboxing works across ChatGPT and Codex clients
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Agent Identity, Authorization, and Secrets · AI Guardrails
Link last checked: 2026-09-24
Auto-review
How Codex routes sandbox-boundary approvals through a reviewer agent
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Agent Identity, Authorization, and Secrets · AI Guardrails
Link last checked: 2026-09-24
Codex Security
Find and remediate vulnerabilities with the Codex Security plugin, CLI, TypeScript SDK, or cloud.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Agent Identity, Authorization, and Secrets · AI Guardrails
Link last checked: 2026-09-24