ai-core/structured-outputs

A way to make an AI chat return data that matches a defined JSON shape, using schemas from Zod, ArkType, or Valibot. The returned data is checked and typed for use in TypeScript.

In plain words
What is it for?
Use it when a chat response must contain predictable fields, such as a person record or another structured object. It also supports receiving that structured data incrementally while the model responds.
Why use it?
It reduces errors caused by free-form AI text that does not follow the structure your code expects. Provider-specific setup is handled for you.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/tanstack/ai/structured-outputs
Any agent
npx skills add TanStack/ai --skill structured-outputs
Clone the repo
git clone --depth 1 https://github.com/TanStack/ai

Made for: Claude Code, Codex.

Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,335 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00128 $0.06335
Opus 5 $0.00064 $0.03168
Sonnet 5 $0.00026 $0.01267
Haiku 4.5 $0.00013 $0.00634

Measured 2d ago against content hash 0fa3e2fec6df, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-core/structured-outputs 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.

packages/ai/skills/ai-core/structured-outputs/SKILL.md · 589 lines

How it starts

The opening of the file, as written. The whole thing — 589 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Structured Outputs

Dependency note: This skill builds on ai-core. Read it first for critical rules. The useChat patterns below build on ai-core/chat-experience — read that for the base hook surface, then come back here for the structured-output specifics.

Setup

import { chat } from '@tanstack/ai'
import { openaiText } from '@tanstack/ai-openai'
import { z } from 'zod'

const person = await chat({
  adapter: openaiText('gpt-5.2'),
  messages: [{ role: 'user', content: 'John Doe, 30' }],
  outputSchema: z.object({
    name: z.string(),
    age: z.number(),
  }),
})

person.name // string — fully typed, no cast
person.age // number

When outputSchema is provided, chat() returns Promise<InferSchemaType<TSchema>> instead of AsyncIterable<StreamChunk>. The result is fully typed.

Adding stream: true switches the return to StructuredOutputStream<InferSchemaType<TSchema>> — incremental JSON deltas plus a terminal validated object. See Pattern 3 below for direct iteration, Pattern 4 for the useChat shape on the client, Pattern 5 for multi-turn structured chats, and Pattern 6 for harness adapters.

Decision: which pattern fits

Building this Use
One prompt in → one typed object out (script, server endpoint, CLI) Pattern 1 (basic) or 2 (nested)
A UI that fills in field by field as the model streams (progressive form, live card) Pattern 4 — useChat({ outputSchema })
Direct iteration of the stream in Node or tests Pattern 3 — async iterable
Users iterate on a structured object across multiple turns (recipe builder, ticket refinement) Pattern 5 — multi-turn structured chat
Tools that gather info, then return a typed object Combine any of the above with tools — see ai-core/tool-calling
A coding agent in a sandbox inspects files, then returns a typed object Pattern 6 — harness outputSchema

Read the full file on GitHub · 589 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. 2d ago First seen · 589 lines · 128 tokens per session scan A 0fa3e2fec6df

Subscribe to this mod's changes

ai-core/structured-outputs is a skill published in the GitHub repository TanStack/ai (3,045 stars, last pushed 2d ago), licensed MIT. It adds 128 tokens to every session and 6,335 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.