OpenAI rolled out Codex plugins across the app, CLI, and IDE extensions, with app auth, reusable skills, and optional MCP servers. Teams should test plugin-backed workflows and permission models before broad rollout.

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.
Imbue released Latchkey, a library that prepends ordinary curl calls so local agents can use SaaS and internal APIs while credentials stay on the developer machine. Try it where agents need many HTTP integrations but should not see raw secrets.
breakingAnthropic said free, Pro, and Max users will hit 5-hour Claude session limits faster on weekdays from 5am to 11am PT, while weekly caps stay the same. Shift long Claude Code jobs off-peak and watch prompt-cache misses.
releaseCline launched Kanban, a local multi-agent board that runs Claude, Codex, and Cline CLI tasks in isolated worktrees with dependency chains and diffs. Teams can use it as a visual control layer for parallel coding agents on repo chores that split cleanly.
releaseMistral released open-weight Voxtral TTS with low-latency streaming, voice cloning, and cross-lingual adaptation, and vLLM Omni shipped day-0 support. Voice-agent teams should compare quality, latency, and serving cost against closed APIs.
releaseGoogle launched Gemini 3.1 Flash Live in AI Studio, the API, and Gemini Live with stronger audio tool use, lower latency, and 128K context. Voice-agent teams should benchmark quality, latency, and thinking settings before switching.
We're rolling out plugins in Codex. Codex now works seamlessly out of the box with the most important tools builders already use, like @SlackHQ, @Figma, @NotionHQ, @gmail, and more. developers.openai.com/codex/plugins
Vercel plugin now supported on OpenAI Codex and Codex CLI. Install it to level up Codex's knowledge and use of Vercel with: • 39 platform skills • 3 specialized agents • Real-time code validation vercel.com/changelog/verc…
Box just launched its plugin within Codex, which means you can take any content within Box and automate workflows around it using the power of a coding agent. Here's a quick example of processing earnings call documents to extract structured data at scale, which you could then Show more
We're rolling out plugins in Codex. Codex now works seamlessly out of the box with the most important tools builders already use, like @SlackHQ, @Figma, @NotionHQ, @gmail, and more. developers.openai.com/codex/plugins
developers.openai.com/codex/plugins Codex 🤝 Plugins "What plugins are: Plugins are installable bundles for reusable Codex workflows. They make it easier to share the same setup across projects or teams, and they can package skills, optional app integrations, and MCP server Show more