Build with an AI coding agent

Install the Catalyst skills in your AI coding agent, sign in, and start one demo. Your agent then shows you a durable workflow or agent surviving a crash, on your own Catalyst account.

Before you begin

• Claude Code, OpenAI Codex, or the GitHub Copilot CLI. For VS Code and other agents, see Other agents and setups.
• Git, and a runtime for the sample's language. The starter prompts use Python by default.

Your agent does everything through the Catalyst MCP server.

1. Install

Run the command for your agent. It installs the Catalyst skills and adds the Catalyst MCP server:

Claude Code

macOS/Linux

claude plugin marketplace add diagridio/catalyst-ai && claude plugin install catalyst-ai@diagrid

Windows

claude plugin marketplace add diagridio/catalyst-ai
claude plugin install catalyst-ai@diagrid

The plugin installs the skills, registers the Catalyst MCP server, and adds the /catalyst-ai:try-workflow and /catalyst-ai:try-agent commands that step 3 uses.

Codex

macOS/Linux

npx skills add diagridio/catalyst-ai --agent codex --skill '*' --yes && codex mcp add catalyst --url https://mcp.cloud.r1.diagrid.io/mcp --oauth-client-id codex

Windows

npx skills add diagridio/catalyst-ai --agent codex --skill '*' --yes
codex mcp add catalyst --url https://mcp.cloud.r1.diagrid.io/mcp --oauth-client-id codex

This installs the skills into .agents/skills/ in the current project, and adds the Catalyst MCP server.

Copilot CLI

macOS/Linux

npx skills add diagridio/catalyst-ai --agent github-copilot --skill '*' --yes && copilot mcp add --transport http catalyst https://mcp.cloud.r1.diagrid.io/mcp

Windows

npx skills add diagridio/catalyst-ai --agent github-copilot --skill '*' --yes
copilot mcp add --transport http catalyst https://mcp.cloud.r1.diagrid.io/mcp

This installs the skills into .agents/skills/ in the current project, and adds the Catalyst MCP server. Then open ~/.copilot/mcp-config.json and add "oauthClientId": "copilot-cli" to the catalyst entry, so Copilot signs in with its registered client ID:

{
  "mcpServers": {
    "catalyst": {
      "type": "http",
      "url": "https://mcp.cloud.r1.diagrid.io/mcp",
      "oauthClientId": "copilot-cli",
      "tools": ["*"]
    }
  }
}

2. Sign in or sign up

Authenticate once:

Claude Code

Run /mcp, choose plugin:catalyst-ai:catalyst, and choose Authenticate.

Codex

codex mcp login catalyst

Copilot CLI

Run /mcp, choose catalyst, and choose Authenticate.

Your browser opens. Sign in, or create a free account, then approve your agent's access. From then on, your agent acts as you.

If you just created your account, verify your email, open catalyst.diagrid.io once to finish setting it up, and then authenticate again.

3. Try the starter prompt

When a process dies mid-task, you normally lose the work, or build retries, state tables, and queues to protect it. On Catalyst, it resumes where it stopped. To see it happen, start your agent and choose a demo. For Codex and the Copilot CLI, start it in the folder where you installed the skills.

Durable workflow

In Claude Code with the plugin, run /catalyst-ai:try-workflow.

In Codex, the Copilot CLI, or Claude Code with skills from npx skills add, give your agent this prompt:

I'm new to Diagrid Catalyst. Show me a durable workflow that survives a crash, using the Catalyst MCP tools for everything in Catalyst, and your shell for git and running the app.
1. Call `catalyst_whoami` and tell me which org I'm signed in to. If that fails, help me sign in.
2. Clone https://github.com/diagridio/catalyst-quickstarts, take the durable workflow sample in my language (Python if unsure), and make sure the app `durable-workflow` exists in project `default`.
3. Get its connection with `catalyst_get_connection`, write the values to a `.env` in the sample folder (gitignored), and start the sample in the background with its environment loaded from it.
4. Run one workflow to completion. Then start one through the sample's crash endpoint, show me with `catalyst_get_workflow_run` that it's RUNNING and waiting, not failed, and wait until I type continue.
5. Restart the app. When the run completes, show me from its history that finished steps ran once and only the step the crash cut off ran again.
6. Explain in at most three sentences why it survived, then offer one next step and wait for my pick. End with this run's console link: https://catalyst.diagrid.io/workflows/<app-id>/<instance-id>?project=<project>.

Your agent clones a sample, runs a workflow, crashes it partway through, and shows you the run resume from where it stopped. It waits for you before the restart, and again at the end.

Durable agent

In Claude Code with the plugin, run /catalyst-ai:try-agent.

In Codex, the Copilot CLI, or Claude Code with skills from npx skills add, give your agent this prompt:

I'm new to Diagrid Catalyst. Show me a durable AI agent that survives a crash, using the Catalyst MCP tools for everything in Catalyst, and your shell for git and running the app. The sample runs on a built-in offline model, so no API key is needed.
1. Call `catalyst_whoami` and tell me which org I'm signed in to. If that fails, help me sign in.
2. Clone https://github.com/diagridio/catalyst-quickstarts and take `agents/langgraph`. With `catalyst_apply`, make sure agent `schedule-planner` exists in project `default`. Catalyst provides its state, pub/sub and registry, so apply only the agent itself.
3. Get its connection with `catalyst_get_connection`, write the values to a `.env` in the sample folder (gitignored), and start `crash_test.py` on port 8001 in the background with its environment loaded from it.
4. Start a run with `POST /crash/run` and `kill_after_seconds`, so the agent dies mid-run. Show me with `catalyst_get_workflow_run` that the run is RUNNING and waiting, not failed, and wait until I type continue.
5. Restart it the same way. When the run completes, show me from its history that the steps finished before the crash ran once and only the one it cut off ran again.
6. Explain in at most three sentences why it survived, then offer one next step and wait for my pick. End with this run's console link: https://catalyst.diagrid.io/workflows/schedule-planner/<instance-id>?project=default.

Your agent clones the LangGraph sample, starts an agent run, kills it partway through, and shows you the run resume from where it stopped. The sample uses a built-in offline model, so it runs as is. It waits for you before the restart, and again at the end.

Open the console link your agent prints to see the run.

More prompts to try

Once the starter demo has worked, try one of these in your own project:

• "Add a durable agent to this project that answers questions about our product, and show me it keeps the conversation after a restart."
• "Add a human approval step to my workflow: pause until I approve, then carry on."
• "Turn this process into a durable workflow:" followed by a description, a Mermaid diagram, or a photo of a whiteboard.
• "Find out why my last workflow run failed, fix the code, and rerun it."
• "Create what this app needs in Catalyst, and show me each piece is ready."

What the skills do

Skill	What it does
catalyst-setup	Connects the session to Catalyst and confirms it works.
catalyst-workflow-scaffold	Adds a durable workflow, with its activities and project wiring, in your repository's language.
catalyst-workflow-from-diagram	Turns a diagram, such as Mermaid, BPMN, or a photo of a whiteboard, into a workflow.
catalyst-agent-scaffold	Adds a durable agent.
catalyst-develop	Runs your app on your machine against Catalyst while you edit it, using connection values from the MCP server.
catalyst-deploy	Moves an app from your laptop into Catalyst.
catalyst-operate	Reads a project's apps, agents, workflow runs, logs, and quotas.
catalyst-debug	Diagnoses a failing app or run, then stops, reruns, or purges runs when you ask it to.
catalyst-workflow-determinism	Checks that workflow code replays safely.
catalyst-activity-idempotency	Makes activities safe to run more than once.

What your agent can change

Your agent acts as you. It can reach the projects your account can reach, and your role limits what it can change.

The skills work through the MCP server's tools, which cover reading, deploying and deleting resources, granting and revoking access, and starting, rerunning, terminating, or purging workflow runs. Your role decides what your agent can change: a read-only role sees the 28 read-only tools, catalyst_get_connection needs write access, and the Catalyst API checks every change against your role. Tools whose changes are permanent are marked destructive, so agents that honor that mark ask you first. Deleting a project, purging runs, and rerunning several runs at once show a preview and wait for a second, confirmed call.

At the default data sharing level, your agent sees names, statuses, and errors. The full level adds workflow input, output, and custom status. See Choose how much the agent sees.

Other agents and setups

• VS Code, Claude Desktop, and claude.ai: connect them to the Catalyst MCP server. To give Copilot in VS Code the skills too, run the npx skills add part of the Copilot CLI command. Support for Cursor is coming soon.

• Install for your user instead of one project: add -g to the npx skills add command.

• Install for several agents at once: repeat -a for each agent:

  npx skills add diagridio/catalyst-ai -a claude-code -a codex -a github-copilot -s '*' -y

  Give each agent its own -a flag. This installs the skills. For Claude Code, use the plugin: it also registers the MCP server and adds the /catalyst-ai:try-workflow and /catalyst-ai:try-agent commands. With skills from npx skills add, give Claude Code the prompt from step 3.

• Keep --yes in every npx skills add command, so a non-interactive run installs the skills.

Catalyst skills and Dapr Skills

The Catalyst skills and the Dapr Skills plugin do different jobs. Dapr Skills scaffolds Dapr Workflow projects for any Dapr environment. The Catalyst skills work with your Catalyst organization: its projects, apps, and workflow runs.

Next steps

🔌

Connect to the Catalyst MCP server

Add the hosted server to Codex, VS Code, Claude Desktop, and more.

🔁

Workflows

Understand the durable workflows your agent scaffolds.