← Experts

Run agents in the cloud, not just locally

Set up Claude Code Routines that run on Anthropic infrastructure even when your computer is off, trigger Managed Agents via REST API or webhooks, and push results to Slack, GitHub, or email — cloud-native agent operations.

1

Expert Install

Copy this to your agent — it will install, configure, and verify everything.

Say to your agent
Read https://clawhub.md/expert/cloud-agent-ops.md and set me up as Cloud Agent Ops

Works on OpenClaw, Claude Code, Telegram, Feishu, and any agent interface. Your agent reads cloud-agent-ops.md and follows the setup steps inside.

2

Talk and handle it

After setup, say these to your agent:

Schedule Claude Code tasks via cron,… Official

  • › "Set up a routine that runs tests every morning at 9am"
  • › "Create a webhook-triggered routine for PR auto-review"
  • › "Schedule a weekly report and post to Slack"

Cloud agents need to interact with… Official

  • › "Check CI status on the release branch"
  • › "Auto-assign reviewers when a PR is opened"
  • › "Create an issue from the routine output"

Delegate the actual coding work to… Official

  • › "Have the routine delegate bug fixes to a coding agent"
  • › "Run a background agent for the long migration script"
  • › "Trigger Codex from a scheduled routine"
▶ View setup file cloud-agent-ops.md

Cloud Agent Ops

Agentic setup file — share this URL with your agent and it will set everything up for you: https://clawhub.md/expert/cloud-agent-ops.md

Goal: Run agents in the cloud, not just locally

What you'll have: Set up Claude Code Routines that run on Anthropic infrastructure even when your computer is off, trigger Managed Agents via REST API or webhooks, and push results to Slack, GitHub, or email — cloud-native agent operations.

Step 1: Install

clawhub install openclaw/cloud-routines openclaw/github openclaw/coding-agent

Step 2: Configure

Each skill may need credentials or auth before it can act on your behalf.

openclaw/cloud-routines

Schedule Claude Code tasks via cron, trigger from GitHub/Slack webhooks, and run Managed Agents in Anthropic's sandbox — the core of cloud agent operations.

  • Ensure Claude Code is installed and authenticated: claude auth login
  • Enable Routines: claude routines enable (requires Max subscription)
  • For webhook triggers, configure your incoming webhook URL in Claude settings

openclaw/github

Cloud agents need to interact with your repo — review PRs, check CI, and create issues as part of automated workflows.

  • Authenticate with the GitHub CLI: run gh auth login and follow the prompts
  • Choose HTTPS or SSH, then log in via browser — no extra tokens needed
  • The skill uses gh under the hood, so all your existing GitHub access applies

openclaw/coding-agent

Delegate the actual coding work to a local or cloud agent — your routines orchestrate, agents execute.

  • Ensure Claude Code is installed: npm install -g @anthropic-ai/claude-code (or see https://claude.ai/code)
  • Optional — for Codex delegation: npm install -g @openai/codex then codex login
  • No extra environment variables needed if Claude Code is already working in your session

Step 3: Try it

After setup, say these to your agent to verify everything works:

openclaw/cloud-routines

  • "Set up a routine that runs tests every morning at 9am"
  • "Create a webhook-triggered routine for PR auto-review"
  • "Schedule a weekly report and post to Slack"

openclaw/github

  • "Check CI status on the release branch"
  • "Auto-assign reviewers when a PR is opened"
  • "Create an issue from the routine output"

openclaw/coding-agent

  • "Have the routine delegate bug fixes to a coding agent"
  • "Run a background agent for the long migration script"
  • "Trigger Codex from a scheduled routine"

Cloud Agent Ops · clawhub.md/expert/cloud-agent-ops

← Experts Browse all skills →