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 Deuz-AI/Deuz-SDK --skill migrate-from-ai-sdkgit clone --depth 1 https://github.com/Deuz-AI/Deuz-SDKWrote 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/deuz-ai/deuz-sdk/migrate-from-ai-sdk)<a href="https://agentmods.dev/skills/deuz-ai/deuz-sdk/migrate-from-ai-sdk"><img src="https://agentmods.dev/badge/skills/deuz-ai/deuz-sdk/migrate-from-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/deuz-ai/deuz-sdk/migrate-from-ai-sdk"><img src="https://agentmods.dev/badge/skills/deuz-ai/deuz-sdk/migrate-from-ai-sdk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00118 | $0.02486 |
| Opus 5 | $0.00059 | $0.01243 |
| Sonnet 5 | $0.00024 | $0.00497 |
| Haiku 4.5 | $0.00012 | $0.00249 |
Grade A, and why
migrate-from-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 11d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migrate from the Vercel AI SDK to @deuz-sdk/core
Both are TypeScript AI SDKs with free functions, a canonical delta stream, schema-typed structured output and a streaming UI protocol, so most of a port is mechanical. Four things are NOT mechanical and decide the shape of the work — read them before editing a single file.
Companion skill: deuz-sdk (same install) documents the target API itself. Use it for anything about how Deuz works; use this skill for the mapping and the porting order.
Verification rule (do not skip)
The AI SDK renames aggressively across majors. Every left-hand name in these rule files was verified against the live docs at ai-sdk.dev on 2026-07-28 ([email protected], AI SDK 7 published 2026-06-25). Before you trust one:
- Read the user's
package.jsonfor the actualai/@ai-sdk/*versions. A v4/v5/v6 app uses different names (toDataStreamResponse,stepCountIs,onStepFinish,system,fullStream,needsApproval,experimental_*). - When a name in their code is not in the mapping tables, DO NOT guess a Deuz equivalent. Grep the Deuz source or say you could not map it.
Right-hand (Deuz) names are verified against the repo source. If an import does not exist in @deuz-sdk/core's package.json exports, it is wrong — check before writing it.
The four decisions
1. Keys become explicit — there is no env read anywhere
@deuz-sdk/core reads NO environment variable and has no hosted gateway (it must run unchanged on Cloudflare Workers). Every provider factory takes apiKey. Read process.env at the app layer, or pass env.X in a Worker.
2. The UI wire is different — both halves of a chat feature move together
Deuz does not speak the AI SDK's UI message protocol. You cannot point the AI SDK's useChat at a Deuz route, or Deuz's useChat at an AI SDK route. Port the route and its client in the same commit.
3. maxSteps defaults to 1 — this is the #1 porting bug
An AI SDK agent loops by default. A Deuz call with tools and no maxSteps runs ONE turn, returns finishReason: 'tool_calls' and no answer. Add an explicit maxSteps to every ported tool-using call.
What ships with it
6 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.
- 11d ago First seen · 113 lines · 118 tokens per session scan A 8e61af469c89
migrate-from-ai-sdk is a skill published in the GitHub repository Deuz-AI/Deuz-SDK (1,203 stars, last pushed 28d ago), licensed MIT. It adds 118 tokens to every session and 2,486 once invoked, about $0.0006 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.
Other skills, from other repositories
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-ai
Use when writing C++ code with axllm for named deployment profiles, generic provider clients, model selection, OpenAI-compatible calls, Responses, Gemini, Anthropic, routers, and balancers.
ax-cpp-gen
Use when writing C++ code with axllm for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.
ax-go-gen
Use when writing Go code with github.com/ax-llm/ax/packages/go for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.
ax-java-gen
Use when writing Java code with dev.axllm:ax for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.
ax-cpp-llm
Use when writing C++ code with axllm for using the generated Ax package, factory functions, package docs, examples, and API reference.