tokens&
For enterprises
Submit
Sign in
tokens&

Build better AI stacks, claim useful opportunities, and give AI infrastructure companies a source-labeled adoption readout they can trust.

For buildersFor enterprises

Product

  • For builders
  • Category rankings
  • Startup credits and perks
  • Agent Skills
  • Platform
  • Submit project, tool, product, or perk

Enterprise

  • Start free company workspace

Community

  • Community
  • Newsletter
  • Events
Xin

© 2026 tokensand, LLC. All rights reserved.

  • Terms
  • Privacy
  • Security
  • Data Processing
  • Status
Agent Skills/Agents SDK build guide
CloudflareAgentsSKILL.mdVerified source

Agent Skill

Agents SDK build guide

Create stateful Workers agents, MCP servers, workflows, queues, and realtime apps.

Install this skillView repository

Vendor-authored source · Apache-2.0 license.

Raw SKILL.mdInstall the Tokens& Agent Pack

Tokens& curated build recipe

An agent with persistent task state

Build a small Cloudflare Agents SDK app that stores a task checklist and restores it after reconnecting. Use public sample tasks, one read-only tool, and bounded model requests.

  1. 1. Check the startup application

    Cloudflare startup infrastructure credits

    First-time technology startups must meet Cloudflare's company, funding, website, and business-email criteria. Credits expire after one year; Workers AI and storage have product caps, and AI Gateway is excluded.

    Read Cloudflare terms
  2. 2. Use the vendor skill

    Agents SDK build guide

    Review the source and install instructions below, then use the skill in your own project.

    See install instructions
  3. 3. Build and show the result

    Save the Build Packet, then attach a demo and a test showing task state survives a reconnect without repeating a completed task.

    Start this Build Packet

Public resources selected by Tokens&. Terms reviewed 2026-09-05; the provider decides eligibility and current limits. This recipe is a suggested project, not a vendor partnership or a completed build.

Skill specification

Declared by Cloudflare in the package front matter. Trigger conditions are what the coding agent matches on before it loads the skill.

View package fields
Agents SDK build guide SKILL.md front matter fields
Skill nameagents-sdk
Trigger conditionsBuild AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agents, or browser automation. Covers Agent class, state management, callable RPC, Workflows, durable execution, queues, retries, observability, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

Install agents-sdk

In a terminal with Node.js, npm and Git, run the command for your agent. The Skills CLI installs the complete package directory, including referenced files within it. Review its install prompt, then start a new agent session. A skill package does not set up an MCP server connection.

Codex

.agents/skills/agents-sdk/SKILL.md

Codex reads `.agents/skills/` as its primary location, which is also the cross-platform default other clients honour.

Project install

npx skills add 'https://github.com/cloudflare/skills/tree/main/skills/agents-sdk' --skill 'agents-sdk' --agent 'codex'
Install for all projects instead

Personal install

npx skills add 'https://github.com/cloudflare/skills/tree/main/skills/agents-sdk' --skill 'agents-sdk' --agent 'codex' --global

SKILL.md

View raw source

Published by Cloudflare under Apache-2.0. Rendered from the package in github.com/cloudflare/skills/tree/main/skills/agents-sdk.

Read full skill instructions

Cloudflare Agents SDK

Your knowledge of the Agents SDK may be outdated. Prefer retrieval over pre-training for any Agents SDK task.

Retrieval Sources

Cloudflare docs: https://developers.cloudflare.com/agents/

TopicDocs URLUse for
Getting startedQuick startFirst agent, project setup
Adding to existing projectAdd to existing projectInstall into existing Workers app
ConfigurationConfigurationwrangler.jsonc, bindings, assets, deployment
Agent classAgents APIAgent lifecycle, patterns, pitfalls
StateStore and sync statesetState

Capabilities

The Agents SDK provides:

  • Persistent state — SQLite-backed, auto-synced to clients via setState
  • Callable RPC — @callable() methods invoked over WebSocket
  • Scheduling — One-time, recurring (scheduleEvery), and cron tasks
  • Workflows — Durable multi-step background processing via AgentWorkflow
  • Durable execution — runFiber() / stash() for work that survives DO eviction
  • Queue — Built-in FIFO queue with retries via queue()
  • Retries — this.retry() with exponential backoff and jitter
  • MCP integration — Connect to MCP servers or build your own with McpAgent
  • Email handling — Receive and reply to emails with secure routing
  • Streaming chat — AIChatAgent with resumable streams, message persistence, tools
  • Server-driven messages — saveMessages, waitUntilStable

FIRST: Verify Installation

npm ls agents  # Should show agents package

If not installed:

npm install agents

For chat agents:

npm install agents @cloudflare/ai-chat ai @ai-sdk/react

Wrangler Configuration

{
  "compatibility_flags": ["nodejs_compat"],
  "durable_objects": {
    "bindings": [{ "name": "MyAgent", "class_name": "MyAgent" }]
  },
  "migrations": [{ "tag": "v1", "new_sqlite_classes": ["MyAgent"] }]
}

Gotchas:

  • Do NOT enable experimentalDecorators in tsconfig (breaks @callable)
  • Never edit old migrations — always add new tags
  • Each agent class needs its own DO binding + migration entry
  • Add "ai": { "binding": "AI" } for Workers AI

Agent Class

import { Agent, routeAgentRequest, callable } from "agents";

type State = { count: number };

export class Counter extends Agent<Env, State> {
  initialState = { count: 0 };

  validateStateChange(nextState: State, source: Connection | "server") {
    if (nextState.count < 0) throw new Error("Count cannot be negative");
  }

  onStateUpdate(state: State, source: Connection | "server") {
    console.log("State updated:", state);
  }

  @callable()
  increment() {
    this.setState({ count: this.state.count + 1 });
    return this.state.count;
  }
}

export default {
  fetch: (req, env) => routeAgentRequest(req, env) ?? new Response("Not found", { status: 404 })
};

Routing

Requests route to /agents/{agent-name}/{instance-name}:

ClassURL
Counter/agents/counter/user-123
ChatRoom/agents/chat-room/lobby

Client: useAgent({ agent: "Counter", name: "user-123" })

Custom routing: use getAgentByName(env.MyAgent, "instance-id") then agent.fetch(request).

Core APIs

TaskAPI
Read statethis.state.count
Write statethis.setState({ count: 1 })
SQL querythis.sql`SELECT * FROM users WHERE id = ${id}`
Schedule (delay)await this.schedule(60, "task", payload)
Schedule (cron)await this.schedule("0 * * * *", "task", payload)
Schedule (interval)await this.scheduleEvery(30, "poll")
RPC method@callable() myMethod() { ... }
Streaming RPC@callable({ streaming: true }) stream(res) { ... }
Start workflowawait this.runWorkflow("ProcessingWorkflow", params)

React Client

import { useAgent } from "agents/react";

function App() {
  const [state, setLocalState] = useState({ count: 0 });

  const agent = useAgent({
    agent: "Counter",
    name: "my-instance",
    onStateUpdate: (newState) => setLocalState(newState),
    onIdentity: (name, agentType) => console.log(`Connected to ${name}`)
  });

  return (
    <button onClick={() => agent.setState({ count: state.count + 1 })}>
      Count: {state.count}
    </button>
  );
}

References

Core

  • [references/state-scheduling.md](references/state-scheduling.md) — State persistence, scheduling, SQL
  • [references/callable.md](references/callable.md) — RPC methods, streaming, timeouts
  • [references/routing.md](references/routing.md) — URL patterns, custom routing, getAgentByName
  • [references/configuration.md](references/configuration.md) — Wrangler config, bindings, Vite setup

Chat & Streaming

  • [references/streaming-chat.md](references/streaming-chat.md) — AIChatAgent, resumable streams, tools
  • [references/client-sdk.md](references/client-sdk.md) — useAgent, useAgentChat, AgentClient
  • [references/server-driven-messages.md](references/server-driven-messages.md) — Trigger patterns, saveMessages
  • [references/human-in-the-loop.md](references/human-in-the-loop.md) — Approval flows, needsApproval

Background Processing

  • [references/workflows.md](references/workflows.md) — Durable Workflows integration
  • [references/durable-execution.md](references/durable-execution.md) — runFiber, stash, surviving eviction
  • [references/queue-retries.md](references/queue-retries.md) — Built-in queue, retry with backoff

Integrations

  • [references/mcp.md](references/mcp.md) — MCP client and server, transports, securing
  • [references/email.md](references/email.md) — Email routing and handling
  • [references/webhooks-push.md](references/webhooks-push.md) — Webhooks, push notifications
  • [references/observability.md](references/observability.md) — Diagnostics-channel events

Experimental

  • [references/think.md](references/think.md) — @cloudflare/think higher-level chat agent
  • [references/voice.md](references/voice.md) — @cloudflare/voice STT/TTS
  • [references/codemode.md](references/codemode.md) — Code Mode for tool orchestration
  • [references/browse-the-web.md](references/browse-the-web.md) — CDP browser tools

More Cloudflare Agent Skills

All Agent Skills

Cloudflare Email Service

Send, receive, route, and test transactional email from Workers and REST APIs.

Backend

Durable Objects builder

Build and review stateful Workers apps with RPC, SQLite storage, alarms, and WebSockets.

Backend

Turnstile setup

Install Turnstile end to end with widget creation, siteverify Worker, and frontend snippets.

Backend

Web performance audit

Measure Core Web Vitals, identify resource bottlenecks, and prioritize page-speed fixes.

Frontend

Workers best practices

Author and review Workers code, wrangler config, bindings, secrets handling, and observability.

Backend

Wrangler CLI guide

Use current Wrangler commands and config for Workers, KV, R2, D1, Queues, and secrets.

Backend

,
validateStateChange
, persistence
RoutingRoutingURL patterns, routeAgentRequest
Callable methodsCallable methods@callable, RPC, streaming, timeouts
SchedulingSchedule tasksschedule(), scheduleEvery(), cron
WorkflowsRun workflowsAgentWorkflow, durable multi-step tasks
HTTP/WebSocketsWebSocketsLifecycle hooks, hibernation
Chat agentsChat agentsAIChatAgent, streaming, tools, persistence
Client SDKClient SDKuseAgent, useAgentChat, React hooks
Client toolsClient toolsClient-side tools, autoContinueAfterToolResult
Server-driven messagesTrigger patternssaveMessages, waitUntilStable, server-initiated turns
Resumable streamingResumable streamingStream recovery on disconnect
EmailEmailEmail routing, secure reply resolver
MCP clientMCP clientConnecting to MCP servers
MCP serverMCP serverBuilding MCP servers with McpAgent
MCP transportsMCP transportsStreamable HTTP, SSE, RPC transport options
Securing MCP serversSecuring MCPOAuth, proxy MCP, hardening
Human-in-the-loopHuman-in-the-loopApproval flows, needsApproval, workflows
Durable executionDurable executionrunFiber(), stash(), surviving DO eviction
QueueQueueBuilt-in FIFO queue, queue()
RetriesRetriesthis.retry(), backoff/jitter
ObservabilityObservabilityDiagnostics-channel events
Push notificationsPush notificationsWeb Push + VAPID from agents
WebhooksWebhooksReceiving external webhooks
Cross-domain authCross-domain authWebSocket auth, tokens, CORS
Readonly connectionsReadonlyshouldConnectionBeReadonly
VoiceVoiceExperimental STT/TTS, withVoice
Browse the webBrowser toolsExperimental CDP browser automation
ThinkThinkExperimental higher-level chat agent class
MigrationsAI SDK v5, AI SDK v6Upgrading @cloudflare/ai-chat
for proactive agent turns
  • React hooks — useAgent, useAgentChat for client apps
  • Observability — diagnostics_channel events for state, RPC, schedule, lifecycle
  • Push notifications — Web Push + VAPID delivery from agents
  • Webhooks — Receive and verify external webhooks
  • Voice (experimental) — STT/TTS via @cloudflare/voice
  • Browser tools (experimental) — CDP-powered browsing via agents/browser
  • Think (experimental) — Higher-level chat agent via @cloudflare/think
  • Durable fiber
    await this.runFiber("name", async (ctx) => { ... })
    Enqueue workthis.queue("handler", payload)
    Retry with backoffawait this.retry(fn, { maxAttempts: 5 })
    Broadcast to clientsthis.broadcast(message)
    Get connectionsthis.getConnections(tag?)