ai-sdk-expert

ai-sdk-expert is an agent for Claude Code from GoogilyBoogily/googilyboogily-claude-power-tools. It costs 77 tokens per session (2,298 once invoked), scanned A, original, MIT.

A specialist agent for Vercel AI SDK version 5, a toolkit for building applications that use language models. It covers streaming responses, model providers, React hooks, tool calling, and related TypeScript patterns.

In plain words
What is it for?
Use it for code involving imports from ai or @ai-sdk, useChat, useCompletion, streamText, generateText, generateObject, model providers, or tool schemas. It does not handle unrelated Next.js routing or React-performance issues.
Why use it?
AI SDK code has version-specific APIs and integration details that can cause type, streaming, or provider problems. The agent first checks whether the issue actually involves the AI SDK.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the ai-agents plugin — 3 agents shipped together

Good fit Use it for code involving imports from ai or @ai-sdk, useChat, useCompletion, streamText, generateText, generateObject, model providers, or tool schemas. It does not handle unrelated Next.js routing or React-performance issues.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/googilyboogily/googilyboogily-claude-power-tools/ai-sdk-expert
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.

Clone the repo
git clone --depth 1 https://github.com/GoogilyBoogily/googilyboogily-claude-power-tools

Made for: Claude Code.

Or install ai-agents, the plugin that ships this one along with the rest of its 3 agents.

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-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/ai-sdk-expert/github.svg)](https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/ai-sdk-expert)
Your own site
<a href="https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/ai-sdk-expert"><img src="https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/ai-sdk-expert/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-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/ai-sdk-expert"><img src="https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/ai-sdk-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,298 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00077 $0.02298
Opus 5 $0.00039 $0.01149
Sonnet 5 $0.00015 $0.00460
Haiku 4.5 $0.00008 $0.00230

Measured 12d ago against content hash 9522130115d5, 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-expert scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Diagnostic: `curl -N http://localhost:3000/api/chat`
plugins/ai-agents/agents/ai-sdk-expert.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI SDK by Vercel Expert (v5 Focused)

You are an expert in the Vercel AI SDK v5 (5.0.15+) with deep knowledge of streaming, model integrations, React hooks, edge runtime, and production AI patterns.

STOP Conditions — Do NOT handle these:

  • Pure Next.js routing/SSR issues with no AI SDK involvement -> nextjs-expert
  • React rendering performance with no AI hooks -> react-performance-expert
  • TypeScript type puzzles unrelated to AI SDK schemas -> type-expert
  • General API design with no streaming/AI -> nodejs-expert
  • If the problem has no AI SDK surface area, recommend the right agent and STOP.

Step 0: Route or Stay

When invoked, first determine if this is yours:

  • AI SDK imports (ai, @ai-sdk/*), useChat, useCompletion, streamText, generateText, generateObject, tool schemas, provider config -> Own it.
  • Next.js-only issue -> "This is a Next.js routing issue. Use nextjs-expert. Stopping here."
  • React perf without AI hooks -> "Use react-performance-expert. Stopping here."

If owning, proceed:

  1. Detect environment (Read/Grep/Glob — prefer internal tools over shell)
  2. Apply v5 patterns
  3. Validate: typecheck -> tests -> build (no watch/serve processes)

Version Detection & Migration

Current: AI SDK v5 (5.0.15+). Key v4->v5 breaks:

  • parameters -> inputSchema in tool definitions
  • Tool results -> output
  • New message types, provider imports moved to @ai-sdk/*
  • Automated migration: npx @ai-sdk/codemod upgrade

Detection:

grep -r '"ai"' package.json           # v5.x vs v4.x
grep -r '@ai-sdk/' package.json       # v5 provider packages
grep -r "inputSchema" --include="*.ts" --include="*.tsx"  # v5 pattern
grep -r "parameters:" --include="*.ts" --include="*.tsx"  # deprecated v4 pattern

Domain Coverage (GitHub Issue-Anchored)

Streaming & Real-time (Issues #7817, #8005, #8088, #7919, #8081)

  • "[Error: The response body is empty.]" (#7817) -> Validate response before parsing
  • "streamText errors when using .transform" (#8005) -> Separate transforms from tool schemas
  • "abort signals trigger onError() instead of onAbort()" (#8088) -> Use signal.addEventListener('abort', ...) separately from error handler
  • Chat route hangs (#7919) -> Check AbortController config, response headers
  • Diagnostic: curl -N http://localhost:3000/api/chat

Read the full file on GitHub · 252 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 · 252 lines · 77 tokens per session scan A 9522130115d5

Subscribe to this mod's changes

ai-sdk-expert is an agent published in the GitHub repository GoogilyBoogily/googilyboogily-claude-power-tools (2 stars, last pushed 4mo ago), licensed MIT. It adds 77 tokens to every session and 2,298 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

wiki-query-agent

Use this agent ONLY when explicitly instructed by a skill (e.g., wiki-synchelper) to perform deep search in repowiki/ for documentation sync tasks. Do NOT use this agent for routine TEngine development tasks — use the tengine-dev skill instead. This agent is NOT a general-purpose TEngine reference tool.

Alex-Rachel/TEngine · 70 tokens

Loan Officer Assistant

Comprehensive loan officer assistant for mortgage and lending professionals — covering borrower intake, pre-qualification, document collection, pipeline management, compliance tracking, rate quoting, and closing coordination across residential, commercial, and consumer lending.

SHAdd0WTAka/Zen-Ai-Pentest · 46 tokens

Section 508 Accessibility Specialist

Expert U.S. federal Section 508 accessibility engineer (the 508 legal baseline is WCAG 2.0 Level AA; WCAG 2.1/2.2 AA are recommended best practice, and ADA Title II requires WCAG 2.1 AA for state/local government) specializing in accessible web development, ARIA implementation, screen reader testing…

SHAdd0WTAka/Zen-Ai-Pentest · 125 tokens

Drupal Shopping Cart Engineer

Expert Drupal e-commerce engineer specializing in Drupal Commerce for product catalog management, payment gateway integration, checkout workflow design, order management, tax and promotion configuration, and high-reliability storefront delivery on Drupal 10/11.

SHAdd0WTAka/Zen-Ai-Pentest · 48 tokens

Global Podcast Strategist

Expert podcast growth specialist focused on show positioning, audience development, content strategy, and monetisation. Transforms raw ideas into authoritative audio brands that compound listeners and revenue over time on Spotify, Apple Podcasts, and YouTube.

SHAdd0WTAka/Zen-Ai-Pentest · 49 tokens

HR Onboarding

Comprehensive HR onboarding specialist for employee orientation, documentation management, compliance tracking, benefits enrollment, culture integration, and new hire support — delivering a seamless first-day-to-first-year experience that drives retention and productivity.

SHAdd0WTAka/Zen-Ai-Pentest · 44 tokens