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 krzysztofsurdy/code-virtuoso --skill vercel-ai-sdkgit clone --depth 1 https://github.com/krzysztofsurdy/code-virtuosoWrote 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/krzysztofsurdy/code-virtuoso/vercel-ai-sdk)<a href="https://agentmods.dev/skills/krzysztofsurdy/code-virtuoso/vercel-ai-sdk"><img src="https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/vercel-ai-sdk/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/krzysztofsurdy/code-virtuoso/vercel-ai-sdk"><img src="https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/vercel-ai-sdk.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 | $0.00059 | $0.03574 |
| Opus 5.5 | $0.00024 | $0.01430 |
| Sonnet 5.5 | $0.00012 | $0.00715 |
| Haiku 4.5 | $0.00006 | $0.00357 |
Grade A, and why
vercel-ai-sdk 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 2d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vercel AI SDK
The AI SDK ships a new major about every five to eight months, and each one renames APIs that earlier code and model memory still use. This skill therefore holds no API listings. It holds the version facts, the decisions the docs do not make for you, and the traps between majors. Fetch the current API for the installed major before writing code that calls it.
Core principles
| Principle | Meaning |
|---|---|
| Read the installed major first | ai 5, 6, and 7 differ in names and result shapes. Docs for the wrong major mislead |
| Fetch, do not recall | Treat any remembered import, option name, or model ID as stale until docs confirm it |
| Cap every loop | Agents stop on conditions you set. Combine a step cap with a terminal tool |
| Gate side effects in code | Use toolApproval for destructive tools. Do not rely on a prompt |
| Client history is untrusted | A browser can send any message list, including tool results |
| Mock the model in unit tests | Real-model calls belong in a small eval set, not in every test |
Version matrix
Checked on 2026-10-21 against npm and Context7 /vercel/ai.
| Package | Current | Notes |
|---|---|---|
ai |
7.0.148 | v7.0.0 released 2026-06-25. Node 22 or later, ESM-only. Peer: zod ^3.25.76 || ^4.1.8 |
ai earlier majors |
6.0.312 (ai-v6 tag), 5.0.279 (ai-v5 tag) |
v6.0.0 on 2025-12-22, v5.0.0 on 2025-07-31. Both still publish patches |
@ai-sdk/react |
4.0.152 | Vue 4.0.148, Svelte 5.0.148. Majors follow their own numbering: ai 6 pairs with @ai-sdk/react 3, ai 5 with 2 |
| Providers | @ai-sdk/openai 4.0.99, @ai-sdk/anthropic 4.0.85, @ai-sdk/gateway 4.0.121 |
Install the version that matches your ai major |
| Add-ons | @ai-sdk/mcp 2.0.81, @ai-sdk/workflow 2.0.80, @ai-sdk/otel 1.0.148 |
MCP client, durable WorkflowAgent, OpenTelemetry |
Read what the project actually runs:
npm ls ai @ai-sdk/react --depth=0 2>/dev/null
pnpm list ai "@ai-sdk/*" --depth=0 2>/dev/null
grep -E '"(ai|@ai-sdk/[a-z-]+)"' package.json
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.
- 2d ago First seen · 185 lines · 59 tokens per session scan A caaca753aa05
vercel-ai-sdk is a skill published in the GitHub repository krzysztofsurdy/code-virtuoso (36 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 3,574 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-22.
Other skills, from other repositories
developing-genkit-js
Develop AI-powered applications using Genkit in Node.js/TypeScript. Use when the user asks about Genkit, AI agents, flows, or tools in JavaScript/TypeScript, or when encountering Genkit errors, validation issues, type errors, or API problems.
ax-signature
This skill helps an LLM generate correct DSPy signature code using @ax-llm/ax. Use when the user asks about signatures, s(), f(), field types, string syntax, fluent builder API, validation constraints, or type-safe inputs/outputs.
ax-cpp-gepa
Use when writing C++ code with axllm for GEPA, Pareto tradeoffs, reflection clients, metric budgets, optimizer state, and artifacts.
aicore-sdk-js
Generate working TypeScript/JavaScript boilerplate for SAP GenAI Hub using @sap-ai-sdk/orchestration, @sap-ai-sdk/foundation-models, @sap-ai-sdk/openai (native OpenAI SDK), @sap-ai-sdk/langchain (LangChain), @sap-ai-sdk/document-grounding (RAG), @sap-ai-sdk/prompt-registry, @sap-ai-sdk/llm-batch (batch jobs)…
qianwen-text
Generate text, have conversations, write code, reason, and call functions with Qwen models. TRIGGER when: user asks to chat with Qwen, generate text, write code with Qwen, use Qwen function calling, or explicitly invokes this skill by name (e.g. use qianwen-text). DO NOT TRIGGER when: general coding questions without…
ai-sdk
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI…