What is llm-zod-jsonschema?

A TypeScript pattern for asking a language model for JSON and checking the result with Zod, a library that validates data against defined rules. It creates a JSON Schema, a standard description of the required data shape, and includes it in the prompt.

Use it when building TypeScript applications that parse structured language-model responses. Define the expected fields once, include the generated schema in the prompt, and validate the returned data with Zod.

It keeps the format shown to the model aligned with the format checked by the program. Invalid or unexpected responses can fail immediately instead of causing harder-to-trace errors later.

llm-zod-jsonschema — Cursor rule for Cursor by omril321

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/omril321/automated-notebooklm

Made for: Cursor.

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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/omril321/automated-notebooklm/llm-zod-jsonschema/github.svg)](https://agentmods.dev/rules/omril321/automated-notebooklm/llm-zod-jsonschema)

Your own site

<a href="https://agentmods.dev/rules/omril321/automated-notebooklm/llm-zod-jsonschema"><img src="https://agentmods.dev/badge/rules/omril321/automated-notebooklm/llm-zod-jsonschema/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.

Your own site · 80×15

<a href="https://agentmods.dev/rules/omril321/automated-notebooklm/llm-zod-jsonschema"><img src="https://agentmods.dev/badge/rules/omril321/automated-notebooklm/llm-zod-jsonschema.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 284 This file is loaded in full into every session.

When invoked 284 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00284	$0.00284
Opus 5	$0.00142	$0.00142
Sonnet 5	$0.00057	$0.00057
Haiku 4.5	$0.00028	$0.00028

Measured 11d ago against content hash b854aa0cce07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

llm-zod-jsonschema 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.

.cursor/rules/llm-zod-jsonschema.mdc · 37 lines

What it actually says

Cursor Rule: llm-zod-jsonschema

Title

Best Practice for LLM Output Parsing with Zod and JSON Schema

Rule

Always use zod-to-json-schema to generate a JSON schema from your Zod schema.
Inject the generated JSON schema into the LLM prompt to instruct the model on the expected output format.
After receiving the LLM output, validate it using the original Zod schema.
This ensures the prompt and validation are always in sync, and provides robust, type-safe, fail-fast error handling.
Do not use StructuredOutputParser.fromZodSchema as the canonical pattern; this approach is now preferred for all LLM output parsing in this project.

Rationale

This pattern ensures schema/prompt synchronization, leverages Zod's type safety, and provides robust validation for all LLM output in TypeScript projects.

Example

import { z } from "zod";
import { zodToJsonSchema } from "zod-to-json-schema";

const outputSchema = z.object({ ... });
const jsonSchema = zodToJsonSchema(outputSchema);

// Inject jsonSchema into the LLM prompt
// After LLM returns output, validate with outputSchema.parse(output)

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.

11d ago First seen · 37 lines · 284 tokens per session scan A b854aa0cce07

Subscribe to this mod's changes

llm-zod-jsonschema is a cursor rule published in the GitHub repository omril321/automated-notebooklm (15 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 284 tokens to every session, about $0.0014 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.

Data and AI Prompting

llm-zod-jsonschema

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Cursor Rule: llm-zod-jsonschema

Title

Rule

Rationale

Example

What this file has done since we first saw it

Other cursor rules, from other repositories

baml

co-dialectic

prompt-routing

prompting-for-qe

prompt-evals

012_GEPA_AIME_Tutorial