ai-sdk-5

ai-sdk-5 is a skill for Claude Code, Codex from Gentleman-Programming/Gentleman-Skills. It costs 28 tokens per session (1,418 once invoked), scanned A, original, MIT.

A guide to Vercel AI SDK 5 patterns for building chat features in web applications. It documents the SDK 5 setup and the changes from version 4.

In plain words
What is it for?
Use it when connecting React chat interfaces to an API, sending messages, tracking loading and errors, or migrating from AI SDK 4.
Why use it?
It helps avoid using the older chat API when building or updating an application for the newer SDK version.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when connecting React chat interfaces to an API, sending messages, tracking loading and errors, or migrating from AI SDK 4.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gentleman-programming/gentleman-skills/ai-sdk-5
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Gentleman-Programming/Gentleman-Skills --skill ai-sdk-5
Clone the repo
git clone --depth 1 https://github.com/Gentleman-Programming/Gentleman-Skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ai-sdk-5

README.md
[![agentmods](https://agentmods.dev/badge/skills/gentleman-programming/gentleman-skills/ai-sdk-5/github.svg)](https://agentmods.dev/skills/gentleman-programming/gentleman-skills/ai-sdk-5)
Your own site
<a href="https://agentmods.dev/skills/gentleman-programming/gentleman-skills/ai-sdk-5"><img src="https://agentmods.dev/badge/skills/gentleman-programming/gentleman-skills/ai-sdk-5/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ai-sdk-5

Your own site · 80×15
<a href="https://agentmods.dev/skills/gentleman-programming/gentleman-skills/ai-sdk-5"><img src="https://agentmods.dev/badge/skills/gentleman-programming/gentleman-skills/ai-sdk-5.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,418 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.01418
Opus 5 $0.00014 $0.00709
Sonnet 5 $0.00006 $0.00284
Haiku 4.5 $0.00003 $0.00142

Measured 12d ago against content hash 9bf57821c2f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ai-sdk-5 scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

curated/ai-sdk-5/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Breaking Changes from AI SDK 4

// ❌ AI SDK 4 (OLD)
import { useChat } from "ai";
const { messages, handleSubmit, input, handleInputChange } = useChat({
  api: "/api/chat",
});

// ✅ AI SDK 5 (NEW)
import { useChat } from "@ai-sdk/react";
import { DefaultChatTransport } from "ai";

const { messages, sendMessage } = useChat({
  transport: new DefaultChatTransport({ api: "/api/chat" }),
});

Client Setup

import { useChat } from "@ai-sdk/react";
import { DefaultChatTransport } from "ai";
import { useState } from "react";

export function Chat() {
  const [input, setInput] = useState("");

  const { messages, sendMessage, isLoading, error } = useChat({
    transport: new DefaultChatTransport({ api: "/api/chat" }),
  });

  const handleSubmit = (e: React.FormEvent) => {
    e.preventDefault();
    if (!input.trim()) return;
    sendMessage({ text: input });
    setInput("");
  };

  return (
    <div>
      <div>
        {messages.map((message) => (
          <Message key={message.id} message={message} />
        ))}
      </div>

      <form onSubmit={handleSubmit}>
        <input
          value={input}
          onChange={(e) => setInput(e.target.value)}
          placeholder="Type a message..."
          disabled={isLoading}
        />
        <button type="submit" disabled={isLoading}>
          Send
        </button>
      </form>

      {error && <div>Error: {error.message}</div>}
    </div>
  );
}

UIMessage Structure (v5)

// ❌ Old: message.content was a string
// ✅ New: message.parts is an array

interface UIMessage {
  id: string;
  role: "user" | "assistant" | "system";
  parts: MessagePart[];
}

type MessagePart =
  | { type: "text"; text: string }
  | { type: "image"; image: string }
  | { type: "tool-call"; toolCallId: string; toolName: string; args: unknown }
  | { type: "tool-result"; toolCallId: string; result: unknown };

// Extract text from parts
function getMessageText(message: UIMessage): string {
  return message.parts
    .filter((part): part is { type: "text"; text: string } => part.type === "text")
    .map((part) => part.text)
    .join("");
}

// Render message
function Message({ message }: { message: UIMessage }) {
  return (
    <div className={message.role === "user" ? "user" : "assistant"}>
      {message.parts.map((part, index) => {
        if (part.type === "text") {
          return <p key={index}>{part.text}</p>;
        }
        if (part.type === "image") {
          return <img key={index} src={part.image} alt="" />;
        }
        return null;
      })}
    </div>
  );
}

Read the full file on GitHub · 237 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 237 lines · 28 tokens per session scan A 9bf57821c2f0

Subscribe to this mod's changes

ai-sdk-5 is a skill published in the GitHub repository Gentleman-Programming/Gentleman-Skills (650 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 1,418 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

claude-api-in-prototypes

Call Claude from your HTML artifacts via window.claude.complete.

asgeirtj/system_prompts_leaks · 19 tokens

langchain

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…

davila7/claude-code-templates · 79 tokens

core

Core package for defining schemas, catalogs, and AI prompt generation for json-render. Use when working with @json-render/core, defining schemas, creating catalogs, or building JSON specs for UI/video generation.

vercel-labs/json-render · 42 tokens

playwright

Playwright E2E testing patterns. Trigger: When writing Playwright E2E tests (Page Object Model, selectors, MCP exploration workflow). For Prowler-specific UI conventions under ui/tests, also use prowler-test-ui.

prowler-cloud/prowler · 50 tokens

thinking-orbs

Add accessible animated AI loading and agent-status indicators with the React thinking-orbs library. Use when a chat, copilot, voice, search, generation, or tool-running interface needs a semantic working, searching, solving, listening, composing, or shaping state; when replacing a generic spinner with an AI activity…

MengTo/Skills · 88 tokens

globe-gl

Use when implementing globe.gl (Globe.GL) for 3D globe data visualization with WebGL/ThreeJS, including setup, data layers (points, arcs, polygons, labels), and integration patterns in plain HTML or React.

MengTo/Skills · 51 tokens