xmtplabs/xmtp-agent-examples / skills/building-agents
building-agents
VerifiedCore XMTP Agent SDK setup and patterns. Use when creating new agents, handling messages, setting up middleware, or configuring environment variables. Triggers on agent setup, XMTP configuration, message handling, or middleware implementation.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.9 KB |
| rules/events-lifecycle.md | markdown | 860 B |
| rules/events-text.md | markdown | 913 B |
| rules/middleware-basics.md | markdown | 1.3 KB |
| rules/middleware-command-router.md | markdown | 1.2 KB |
| rules/setup-environment.md | markdown | 716 B |
| rules/setup-from-env.md | markdown | 1.1 KB |
rules/middleware-basics.md
View on GitHub---
title: Create and use middleware
impact: MEDIUM
tags: middleware, agent, flow control
---
## Create and use middleware
Middleware lets you intercept and process messages before they reach event handlers.
**Basic middleware:**
```typescript
import { Agent, AgentMiddleware, isText } from "@xmtp/agent-sdk";
const onlyText: AgentMiddleware = async (ctx, next) => {
if (isText(ctx.message)) {
// Continue to next middleware
await next();
}
// Break middleware chain (return without calling next)
return;
};
agent.use(onlyText);
```
**Middleware flow control:**
1. `await next()` - Continue to next middleware
2. `return` - Stop the chain, prevent events from firing
3. `throw` - Trigger error-handling middleware
**Multiple middleware:**
```typescript
// Register one at a time
agent.use(middleware1);
agent.use(middleware2);
// Or as an array (executed in order)
agent.use([middleware1, middleware2, middleware3]);
```
**Error-handling middleware:**
```typescript
import { AgentErrorMiddleware } from "@xmtp/agent-sdk";
const errorHandler: AgentErrorMiddleware = async (error, ctx, next) => {
if (error instanceof Error) {
await next(`Handled: ${error.message}`);
} else {
await next(error);
}
};
agent.errors.use(errorHandler);
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |