agents-sdk/SKILL.md
Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks.
npx skillsauth add lidge-jun/cli-jaw-skills agents-sdkInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Not to be confused with the OpenAI Agents SDK (Python-based agent orchestration). This skill covers Cloudflare's Agents SDK for building stateful agents on Workers.
Prefer retrieval over pre-training — the Agents SDK evolves rapidly. Current version: v0.14.0 (June 2, 2026).
Fetch current docs from https://github.com/cloudflare/agents/tree/main/docs before implementing.
| Topic | Doc | Use for |
|-------|-----|---------|
| Getting started | docs/getting-started.md | First agent, project setup |
| State | docs/state.md | setState, validateStateChange, persistence |
| Routing | docs/routing.md | URL patterns, routeAgentRequest, basePath |
| Callable methods | docs/callable-methods.md | @callable, RPC, streaming, timeouts |
| Scheduling | docs/scheduling.md | schedule(), scheduleEvery(), cron |
| Workflows | docs/workflows.md | AgentWorkflow, durable multi-step tasks |
| HTTP/WebSockets | docs/http-websockets.md | Lifecycle hooks, hibernation |
| Email | docs/email.md | Email routing, secure reply resolver |
| MCP client | docs/mcp-client.md | Connecting to MCP servers |
| MCP server | docs/mcp-servers.md | Building MCP servers with McpAgent |
| Client SDK | docs/client-sdk.md | useAgent, useAgentChat, React hooks |
| Human-in-the-loop | docs/human-in-the-loop.md | Approval flows, pausing workflows |
| Resumable streaming | docs/resumable-streaming.md | Stream recovery on disconnect |
Cloudflare docs: https://developers.cloudflare.com/agents/
The Agents SDK provides:
@callable() methods invoked over WebSocketscheduleEvery), cron, and declarative scheduled tasks (v0.14+)AgentWorkflow, with reasoning steps (v0.14+)McpAgentAIChatAgent with resumable streams and hardened recovery (v0.14+)useAgent, useAgentChat for client appsnpm ls agents # Should show agents package
If not installed:
npm install agents
{
"durable_objects": {
"bindings": [{ "name": "MyAgent", "class_name": "MyAgent" }]
},
"migrations": [{ "tag": "v1", "new_sqlite_classes": ["MyAgent"] }]
}
import { Agent, routeAgentRequest, callable } from "agents";
type State = { count: number };
export class Counter extends Agent<Env, State> {
initialState = { count: 0 };
// Validation hook - runs before state persists (sync, throwing rejects the update)
validateStateChange(nextState: State, source: Connection | "server") {
if (nextState.count < 0) throw new Error("Count cannot be negative");
}
// Notification hook - runs after state persists (async, non-blocking)
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 })
};
Requests route to /agents/{agent-name}/{instance-name}:
| Class | URL |
|-------|-----|
| Counter | /agents/counter/user-123 |
| ChatRoom | /agents/chat-room/lobby |
Client: useAgent({ agent: "Counter", name: "user-123" })
| Task | API |
|------|-----|
| Read state | this.state.count |
| Write state | this.setState({ count: 1 }) |
| SQL query | this.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 workflow | await this.runWorkflow("ProcessingWorkflow", params) |
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>
);
}
development
Native Web UI structured renderer schemas for compose-block drafts, search-results cards, dataframe tables, chart-json charts, and diff output
tools
Unified search hub. Route any web/real-time/X lookup through a 4-tier escalation: built-in web search → cli-jaw browser CDP → progrok Grok OAuth → web-ai (Grok Expert / GPT Pro). Use for: search, 검색, web search, latest news, real-time info, X/Twitter, fact lookup, deep research.
development
UI/UX intent discovery, design vocabulary, product personalities, UX state patterns, typography line break judgment, favicon/product logo design, and logo trust section design. Use when user design direction is vague, when building onboarding/empty/error states, when setting up favicons or product logos, or when referencing a product aesthetic.
development
Canonical owner of module boundary rules, circular dependency detection/prevention, implicit coupling taxonomy, barrel/re-export discipline, and boundary-only defensive programming. Referenced by dev, dev-code-reviewer, dev-backend, dev-frontend stubs.