Help us improve
Share bugs, ideas, or general feedback.
From cloudflare-agents
Builds AI agents on Cloudflare Workers with tool integration, MCP protocol support, LLM providers (OpenAI, Anthropic, Gemini), and bindings (D1, KV, R2, Durable Objects).
npx claudepluginhub secondsky/claude-skills --plugin cloudflare-agentsHow this skill is triggered — by the user, by Claude, or both
Slash command
/cloudflare-agents:cloudflare-agentsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**Last Updated**: 2025-11-21
references/advanced-features.mdreferences/agent-api.mdreferences/configuration-guide.mdreferences/error-catalog.mdreferences/http-sse-guide.mdreferences/mcp-integration.mdreferences/patterns-concepts.mdreferences/state-management.mdreferences/websockets-guide.mdtemplates/basic-agent.tstemplates/browser-agent.tstemplates/calling-agents-worker.tstemplates/chat-agent-streaming.tstemplates/hitl-agent.tstemplates/mcp-server-basic.tstemplates/rag-agent.tstemplates/react-useagent-client.tsxtemplates/scheduled-agent.tstemplates/state-sync-agent.tstemplates/websocket-agent.tsBuilds AI agents on Cloudflare Workers with state management, durable workflows, WebSockets, scheduling, and React hooks. Activates for stateful agents, chat, voice, or browser automation.
Builds text, realtime voice, and multi-agent apps with OpenAI Agents SDK in JavaScript/TypeScript. Covers tools, guardrails, workflows, templates, and fixes Zod schema errors, tool calls, infinite loops.
Builds MCP (Model Context Protocol) servers on Cloudflare Workers using TypeScript SDK, templates for tools/resources/prompts, and Durable Objects.
Share bugs, ideas, or general feedback.
Last Updated: 2025-11-21
export default {
async fetch(request, env, ctx) {
const agent = {
tools: [
{ name: 'getTodo', handler: async ({id}) => ({id, title: 'Task'}) }
],
async run(input) {
return await processWithLLM(input, this.tools);
}
};
return Response.json(await agent.run(await request.text()));
}
};
const agent = {
tools: [...],
systemPrompt: 'You are a helpful assistant',
model: 'gpt-4o',
async run(input) {
// Process with LLM
}
};
references/patterns-concepts.md (317 lines) - What is Cloudflare Agents, patterns & concepts, critical rules, known issues preventionreferences/configuration-guide.md (152 lines) - Complete configuration deep divereferences/agent-api.md (115 lines) - Complete Agent Class API referencereferences/http-sse-guide.md (74 lines) - HTTP & Server-Sent Eventsreferences/websockets-guide.md (110 lines) - WebSocket integrationreferences/state-management.md (388 lines) - State management, scheduled tasks, workflowsreferences/mcp-integration.md (130 lines) - Model Context Protocol integrationreferences/advanced-features.md (637 lines) - Browser automation, RAG, AI model integration, calling agents, client APIsreferences/error-catalog.md (10 lines) - Common errors and solutionstemplates/basic-agent.ts - Basic agent setuptemplates/browser-agent.ts - Browser automationtemplates/calling-agents-worker.ts - Calling other agentstemplates/chat-agent-streaming.ts - Streaming chat agenttemplates/hitl-agent.ts - Human-in-the-looptemplates/mcp-server-basic.ts - MCP server integrationtemplates/rag-agent.ts - RAG implementationtemplates/react-useagent-client.tsx - React client integrationtemplates/scheduled-agent.ts - Scheduled taskstemplates/state-sync-agent.ts - State synchronizationtemplates/websocket-agent.ts - WebSocket agenttemplates/workflow-agent.ts - Workflows integrationtemplates/wrangler-agents-config.jsonc - Wrangler configurationOfficial Docs: https://developers.cloudflare.com/cloudflare-for-platforms/cloudflare-agents/