OpenAI Codex Plugins Expand AI Capabilities

OpenAI Codex enhances its AI with plugins for external data access and skills for executing custom workflows.

Abstract visualization of interconnected data nodes representing OpenAI Codex plugins and skills.
Visualizing the integration of external tools and custom workflows within OpenAI Codex.· OpenAI News

OpenAI is enhancing its Codex platform with plugins and skills, aiming to make the AI more contextually aware and process-driven. These additions allow Codex to interact with external applications and adhere to specific operational playbooks.

According to OpenAI News, plugins serve as connectors, enabling Codex to access information from services like Google Drive or email inboxes. This integration eliminates the need for manual data transfer, allowing users to simply ask Codex to utilize information from connected sources.

To access these features, users can find plugin and skill management options in the top-left corner of the Codex interface. The platform offers recommended and installed plugins, a browseable library, and options to create new ones, though creation typically demands more technical expertise.

Skills: Codifying Team Processes

Skills function as customizable workflows, teaching Codex how a specific team or company handles a task. This is crucial for tasks that vary significantly across organizations, such as generating newsletters or preparing client reports with a consistent brand voice.

For instance, a skill can instruct Codex on the precise format for company newsletters, the required steps for pulling account data, or how to maintain a specific brand voice in customer communications.

To invoke a skill within a thread, users press '$' and select the desired skill. For example, a command like "$customer-update Create a weekly customer update using the notes and files in this folder" would trigger a pre-defined process.

The distinction is clear: plugins are for accessing external information, while skills are for executing internal processes. Combining both allows Codex to follow team procedures while leveraging data from connected tools, exemplified by a command that uses a Google Drive plugin to fetch files and then applies a team's standard format for an email update.

This expansion of OpenAI's Codex plugins signifies a move towards more integrated and compliant AI assistants in professional environments.

© 2026 StartupHub.ai. All rights reserved. You may not republish this article in full without a license. Search engines and AI research tools may crawl and summarize for reference. Bulk reproduction or model training requires a license. See our terms.
Daniel Singer

Written by

Daniel Singer

Editor, StartupHub.ai

Daniel Singer is the editor of StartupHub.ai, a technology expert and thought leader on AI and its applications across sectors, from fintech and healthcare to developer tooling and consumer software. He writes and tests the tools covered here thoroughly and regularly, and built StartupHub.ai to give founders, operators and buyers a clearer read on what they are actually being sold.