Codex launches plugins for Slack, Figma, Gmail, and Google Drive

• OpenAI rolled out Codex plugins across the app, CLI, and IDE extensions, adding first-party integrations for tools including Slack, Figma, Notion, Gmail, and Google Drive launch thread rollout details.
• The new plugin model packages reusable workflows, app auth, and optional MCP server configs together, so teams can share the same setup across projects instead of re-wiring tools per environment plugin definition plugin docs.
• OpenAI also reset Codex usage limits "across all plans" during the rollout, explicitly to let users experiment with the new plugin system usage reset.
• Early ecosystem plugins already go beyond code generation: Vercel says its Codex plugin ships with 39 platform skills, 3 specialized agents, and real-time code validation, while Box is showing document-to-JSON extraction workflows on top of enterprise content Vercel plugin Box demo.

OpenAI's launch thread says Codex now "works seamlessly out of the box" with tools builders already use, naming Slack, Figma, Notion, Gmail, and more. The companion rollout details adds that plugins are available in the Codex app, Codex CLI, and IDE extensions, which makes this a platform-wide change rather than a single-client feature.

The initial directory shown in

includes GitHub, Slack, Notion, Linear, Gmail, Google Calendar, Google Drive, Figma, Hugging Face, Netlify, Vercel, Cloudflare, and Sentry. That matters for engineering workflows because the launch is not limited to source control or terminal actions; it reaches planning, design, docs, deploy, incident, and comms surfaces that usually sit outside the agent loop.

OpenAI also tied the rollout to higher usage headroom. According to the usage reset, Codex limits were reset "across all plans" so users could try the new plugins immediately.

OpenAI's plugin definition describes plugins as "installable bundles for reusable Codex workflows." In practice, one plugin can combine three layers: skills, which are prompts describing workflows; apps, which handle integrations or connector mappings; and MCP servers, which provide remote tools or shared context. The broader plugin docs also describe local and remote marketplaces, including team-controlled distribution and policy.

That packaging model is the real implementation change. Instead of separately stitching prompts, auth, and tool configuration into every workspace, teams can publish a single plugin and reuse it across projects. OpenAI says developers can build their own plugins and share them internally, and the same announcement says the skills library will grow alongside the plugin catalog.

A short CLI demo in CLI install demo shows the flow directly: list plugins, install one, and make it available in the existing Codex workflow rather than switching products.

The clearest early signal is that plugins are becoming opinionated workflow packs, not just raw connectors. Vercel's Codex plugin post says its plugin adds 39 platform skills, 3 specialized agents, and real-time code validation. That suggests vendors can teach Codex platform-specific patterns instead of merely exposing APIs.

Box's launch demo shows the same pattern in enterprise content: a coding agent processes earnings-call documents and emits structured JSON. OpenAI staff and early users are also describing non-code tasks such as calendar management, bug triage, drafting Google Slides from a corporate template, and Slack-plus-Gmail automations internal workflow Slides example.

The consistent theme across these examples is that Codex is moving from repository-bound coding toward cross-tool operational work. Plugins make the agent useful before code is written and after it ships, which is exactly how OpenAI framed the launch in its announcement thread.