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.
npx skills add vaquarkhan/Fullstack-development-agent-skills --skill vercel-ai-sdk-streaminggit clone --depth 1 https://github.com/vaquarkhan/Fullstack-development-agent-skillsWrote 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.
[](https://agentmods.dev/skills/vaquarkhan/fullstack-development-agent-skills/vercel-ai-sdk-streaming)<a href="https://agentmods.dev/skills/vaquarkhan/fullstack-development-agent-skills/vercel-ai-sdk-streaming"><img src="https://agentmods.dev/badge/skills/vaquarkhan/fullstack-development-agent-skills/vercel-ai-sdk-streaming/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.
<a href="https://agentmods.dev/skills/vaquarkhan/fullstack-development-agent-skills/vercel-ai-sdk-streaming"><img src="https://agentmods.dev/badge/skills/vaquarkhan/fullstack-development-agent-skills/vercel-ai-sdk-streaming.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00048 | $0.00518 |
| Opus 5 | $0.00024 | $0.00259 |
| Sonnet 5 | $0.00010 | $0.00104 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
vercel-ai-sdk-streaming 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vercel AI SDK Streaming
Use When
- Implementing streaming chat or copilot UX in Next.js App Router
- Using Vercel AI SDK (ai package) with OpenAI, Anthropic, or custom providers
- Pairing with
skills/nextjs-app-router-and-streaming-uiandskills/ai-llm-integration-in-fullstack-apps
Workflow
- Keep provider API keys server-side only — Route Handlers or server actions.
- Use streamText/generateText with typed tools and maxSteps limits.
- Wire useChat/useAssistant on client with optimistic UI and error states.
- Pass abortSignal from request for client disconnect cancellation.
- Log usage in onFinish; rate limit per user/session at edge or API.
- Test streaming contracts with integration tests and mock language model.
Required Checks
- API keys never imported in client components
- maxSteps and token budgets configured per endpoint
- Tool calls authorized per user — not global admin tools
- Stream errors surfaced to UI — not silent hangs
Examples And Templates
See examples/ for side-by-side good vs bad patterns agents commonly get wrong.
See templates/ for copy-paste starters aligned with this skill.
Decision Framework
- streamText for chat UX; generateObject for structured form fill.
- Edge runtime only when latency dominates and deps are compatible.
- Persist messages server-side for compliance — not only browser state.
- AI SDK UI components for rapid UX; headless hooks for custom design systems.
Common Rationalizations And Rebuttals
- "Client-side OpenAI is simpler." -> Exposes keys and bypasses auth; always server proxy.
- "Unlimited tool steps." -> Runaway cost; cap steps and tool allowlist.
- "Streaming skips validation." -> Validate tool inputs/outputs same as REST APIs.
Evidence Pack
- Route handler test with mock stream
- Rate limit configuration and burst test
- UX recording of error/retry behavior
- Token usage dashboard sample per feature
Exit Criteria
- Streaming chat works with abort and error handling
- Keys and auth remain server-side
- Tool calling respects user authorization and step limits
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 61 lines · 48 tokens per session scan A 8d0273646b1c
vercel-ai-sdk-streaming is a skill published in the GitHub repository vaquarkhan/Fullstack-development-agent-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 518 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
igniteui-wc-choose-components
Identify and select the right Ignite UI Web Components for your app UI, then navigate to official docs, usage examples, and API references.
nextjs-expert
Expert knowledge in Next.js framework, Server-Side Rendering, Static Site Generation, App Router, Server Components, and full-stack React applications. Use when the user mentions React, SSR, SSG, the App Router, React Server Components, or full stack, or when the task involves Next.js Fundamentals, App Router…
remix-expert
Expert knowledge in Remix framework, nested routing, loaders, actions, progressive enhancement, and building resilient full-stack web applications. Use when the user mentions React, nested routing, loaders, actions, progressive enhancement, or full stack, or when the task involves Remix Fundamentals, Routing System…
nifra-web
Use when building the full-stack side of a Nifra app - file routes, layouts, loaders and actions, forms, server functions, streaming SSR, islands, SSG and ISR, the query cache, and the React, Vue, Solid, Svelte, or Preact render adapters. Covers the client/server boundary rules and the hydration errors that boundary…
cometchat-nextjs-patterns
Framework-specific patterns for integrating CometChat React UI Kit v6 into Next.js projects (App Router and Pages Router). Covers SSR prevention, provider setup, route placement, API routes, and common pitfalls.
cometchat-react-patterns
Framework-specific patterns for integrating CometChat React UI Kit v6 into React projects (Vite or CRA). Covers provider setup, routing, layout integration, env vars, and common pitfalls.