docs: Update agent skills page for the new Runpod skills plugin

get-started/agent-skills.mdx

@@ -1,42 +1,68 @@
 ---
 title: "Agent skills for AI coding tools"
 sidebarTitle: "Agent skills"
-description: "Manage GPU workloads on Runpod with coding agents like Claude Code and Cursor."
+description: "Manage GPU workloads on Runpod with coding agents like Claude Code, Codex, and Cursor."
 tag: "NEW"
 ---
 
-Agent skills make it easier for coding agents to use Runpod directly from your editor or terminal. Once installed, you can ask your agent to create Pods, deploy Serverless endpoints, manage templates, and more, all through natural language.
+The Runpod skills plugin teaches your coding agent how to run GPU workloads on Runpod. Once installed, you can ask your agent to create Pods, deploy Serverless endpoints, transfer files, or deploy your own code with Flash, all in natural language. A built-in router sends each request to the right skill, so you don't need to know which tool applies.
 
-These skills work with [Claude Code](https://docs.anthropic.com/en/docs/claude-code), [Cursor](https://www.cursor.com/), [GitHub Copilot](https://github.com/features/copilot), [Windsurf](https://codeium.com/windsurf), [Cline](https://github.com/cline/cline), and [17+ other AI agents](https://skills.sh/).
+It works with [Claude Code](https://docs.anthropic.com/en/docs/claude-code), [Codex](https://github.com/openai/codex), [Cursor](https://www.cursor.com/), [GitHub Copilot](https://github.com/features/copilot), [Windsurf](https://codeium.com/windsurf), [Cline](https://github.com/cline/cline), and [many other AI agents](https://skills.sh/).
 
-## Installation
+## Quick start
 
-Install the Runpod skills package in your project:
+Install the skills with a single command that works with every agent:
 
 ```bash
 npx skills add runpod/skills
 ```
 
-Restart your agent after installation.
+Next, install the Runpod CLI that the skills rely on (skip this if you already have it):
 
-If you plan to use the `runpodctl` skill, you also need to [install the Runpod CLI](/runpodctl/overview) and run the setup command to configure your [API key](/get-started/api-keys) and SSH keys:
+```bash
+curl -sSL https://cli.runpod.net | bash
+# or with Homebrew:
+brew install runpod/runpodctl/runpodctl
+```
+
+Then authenticate with your [Runpod API key](/get-started/api-keys). The same key works for the CLI, Flash, and the bundled MCP server:
 
 ```bash
+# Set the key for the current shell (add to ~/.zshrc or ~/.bashrc to persist):
+export RUNPOD_API_KEY=<key>
+
+# Or save it permanently to ~/.runpod/config.toml:
 runpodctl doctor
 ```
 
-## Available skills
+That's it — restart your agent and [get started](#getting-started).
+
+## Getting started
+
+There are no commands to memorize: describe what you want, and the router picks the right skill (prompting you if something like an API key is still missing). Confirm it's wired up by asking:
 
-The Runpod skills package includes two skills:
+- "List my Runpod endpoints"
+
+If your endpoints come back, you're set — see [What you can do](#what-you-can-do) for more examples.
+
+## What's included
+
+The plugin installs a router and a set of focused skills:
 
 | Skill | Description |
 |-------|-------------|
-| **Flash** | Build and deploy AI workloads using the `runpod-flash` SDK. Write code locally and deploy to remote GPUs/CPUs. |
-| **runpodctl** | Manage GPU Pods, Serverless endpoints, templates, network volumes, and models through the Runpod CLI. |
+| **runpod** | Router and entry point. Reads your task and hands it to the right skill. |
+| **runpod-mcp** | Manages Pods, endpoints, templates, network volumes, registries, and billing through the Runpod MCP server. |
+| **runpodctl** | Manages the same resources from the [Runpod CLI](/runpodctl/overview), plus Hub deployments, file transfers, SSH keys, and model caching. |
+| **flash** | Writes and deploys your own Python code to Runpod Serverless using the [runpod-flash](/flash/overview) SDK. |
+| **companion-clis** | Uses supporting CLIs such as Hugging Face, Docker, and the AWS CLI when a task needs them. |
+| **runpod-usage** | Provides conceptual knowledge about Pods, Serverless, storage, and GPU selection. |
+
+The plugin also includes a collection of worked, end-to-end reference tasks, such as deploying a Whisper endpoint or running a model on a Pod, that guide your agent through common workflows.
 
 ## What you can do
 
-Once installed, you can ask your AI agent to perform tasks like the following:
+Once installed, you can ask your agent to perform tasks like the following:
 
 | Category | Example prompt |
 |----------|----------------|
@@ -49,24 +75,84 @@ Once installed, you can ask your AI agent to perform tasks like the following:
 | Deploy with Flash | "Deploy this function to a remote GPU with Flash" |
 | Local development | "Start a local dev server with Flash" |
 
-### Flash skill
+## Native install options
+
+The `npx skills add` command above works everywhere. If you'd rather install the plugin through your agent's native marketplace, use the route for your agent below. Each route installs the same router and skills.
 
-The Flash skill lets your agent use the [runpod-flash](/flash/overview) SDK to build and deploy functions to Runpod Serverless. Your agent can generate and deploy code like the following:
+### Claude Code
 
-```python
-from runpod_flash import Endpoint, GpuGroup
+Add the marketplace, install the plugin, then reload:
 
-@Endpoint(name="my-worker", gpu=GpuGroup.AMPERE_80, workers=5, dependencies=["torch"])
-async def compute(data):
-    import torch
-    return {"sum": torch.tensor(data, device="cuda").sum().item()}
+```bash
+/plugin marketplace add runpod/skills
+/plugin install runpod@runpod
+/reload-plugins
 ```
 
-For more details on endpoint types and configuration, see [Create endpoints with Flash](/flash/create-endpoints).
+Installing the plugin also wires up the hosted Runpod MCP server. To authenticate it, run `/mcp`, select **runpod**, and choose **Sign in with Runpod**.
+
+### Codex
+
+```bash
+codex plugin marketplace add https://github.com/runpod/skills.git
+```
+
+Run `codex /plugins`, open the **Runpod** tab, and install (reload if prompted). If the Runpod MCP tools don't appear, add the hosted server manually:
+
+```bash
+codex mcp add runpod --transport http https://mcp.getrunpod.io/
+```
+
+### Gemini
+
+Gemini can install the plugin natively through the bundled `gemini-extension.json`. Follow your client's extension documentation to add it.
+
+## Connecting the MCP server on other agents
 
-### runpodctl skill
+The hosted Runpod MCP server gives your agent structured control-plane tools for managing Pods, endpoints, and other resources. Claude Code sets it up automatically during a native install. On other agents, run the guided installer, which detects your agent and configures the connection:
+
+```bash
+npx @runpod/mcp-server@latest add
+```
+
+The installer authenticates the MCP server for you. To reuse the API key you already set instead, pass it as a bearer header when you add the server. For example, in Claude Code:
+
+```bash
+claude mcp add --transport http runpod -s user https://mcp.getrunpod.io/ \
+  --header "Authorization: Bearer $RUNPOD_API_KEY"
+```
+
+## Update and uninstall
+
+To update the plugin to the latest version:
+
+```bash
+# Claude Code:
+/plugin marketplace update runpod
+
+# Codex:
+codex plugin marketplace upgrade runpod
+
+# skills.sh:
+npx skills add runpod/skills
+```
+
+In Claude Code, run `/reload-plugins` after updating.
+
+To uninstall:
+
+```bash
+# Claude Code:
+/plugin uninstall runpod@runpod
+
+# Codex:
+codex plugin marketplace remove runpod
+
+# skills.sh:
+npx skills remove runpod
+```
 
-The runpodctl skill gives your agent access to the full [Runpod CLI](/runpodctl/overview) for managing Pods, Serverless endpoints, templates, network volumes, and file transfers.
+If a command reports a name mismatch, list what's installed first with `/plugin marketplace list` (Claude Code), `codex plugin marketplace list` (Codex), or `npx skills list` (skills.sh), then use the name shown.
 
 ## Learn more