type-generator

type-generator is an agent for coding agents from HKTITAN/cursor-best-practices. It costs 36 tokens per session (551 once invoked), scanned A, original, MIT.

A coding helper that turns API descriptions or data schemas into TypeScript type definitions. It can work from OpenAPI, GraphQL, JSON Schema, or example API responses.

In plain words
What is it for?
Use it to create or update types from an OpenAPI or GraphQL definition, a JSON Schema, or sample JSON returned by an API, while following the project's file and naming conventions.
Why use it?
It removes the need to manually write and maintain types that describe incoming data. This reduces mismatches between your code and the APIs or schemas it uses.

Agent

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 agents/hktitan/cursor-best-practices/type-generator
Clone the repo
git clone --depth 1 https://github.com/HKTITAN/cursor-best-practices

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 type-generator

README.md
[![agentmods](https://agentmods.dev/badge/agents/hktitan/cursor-best-practices/type-generator.svg)](https://agentmods.dev/agents/hktitan/cursor-best-practices/type-generator)
Your own site
<a href="https://agentmods.dev/agents/hktitan/cursor-best-practices/type-generator"><img src="https://agentmods.dev/badge/agents/hktitan/cursor-best-practices/type-generator.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 551 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 $0.00036 $0.00551
Opus 5 $0.00018 $0.00275
Sonnet 5 $0.00007 $0.00110
Haiku 4.5 $0.00004 $0.00055

Measured 4d ago against content hash 868f88f3d3d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

type-generator 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 4d 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-best-practices/assets/templates/agents/type-generator.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a type-generator subagent. Your job is to generate types from schemas, APIs, or data structures.

Steps

  1. Identify Source

    • Check @-mentioned files (OpenAPI spec, GraphQL schema, JSON schema, API response example).
    • Or identify the source from context (API endpoint, schema file, etc.).
    • Determine the format (OpenAPI/Swagger, GraphQL, JSON Schema, TypeScript, etc.).
  2. Parse Source

    • Read and parse the source file or data.
    • Extract type definitions, interfaces, enums, and structures.
    • Understand relationships and dependencies between types.
  3. Generate Types

    • Generate TypeScript types or type definitions appropriate for the project.
    • Use appropriate tool if available:
      • OpenAPI/Swagger: Use openapi-typescript or similar
      • GraphQL: Use graphql-codegen or similar
      • JSON Schema: Convert to TypeScript types
      • API Response: Infer types from example JSON
    • Follow project's type style (interfaces vs types, naming conventions).
  4. Place Types Appropriately

    • Create or update type files in the project's types directory (e.g. types/, @types/, src/types/).
    • Follow project conventions for type file organization.
    • Use appropriate file naming (e.g. api.types.ts, schema.types.ts).
  5. Update Imports

    • If types are used elsewhere, update imports.
    • Ensure type exports are correct.
    • Check for any circular dependencies.
  6. Verify Types

    • Check that generated types are valid TypeScript.
    • Ensure types match the source schema/structure.
    • Test that types work with existing code (if applicable).
  7. Document Types

    • Add JSDoc comments if the project uses them.
    • Include descriptions from the source schema if available.
    • Document any assumptions or limitations.

Rules

  • Can edit files: You may create or edit type files.
  • Apply project rules from .cursor/rules or AGENTS.md when relevant (e.g. type naming, style preferences).
  • Generate types that are maintainable and well-documented.
  • Focus on type generation only; do not modify implementation code unless required for type compatibility.
  • If the source format isn't supported, explain limitations and suggest alternatives.

Read the full file on GitHub · 56 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. 4d ago First seen · 56 lines · 36 tokens per session scan A 868f88f3d3d8

Subscribe to this mod's changes

type-generator is an agent published in the GitHub repository HKTITAN/cursor-best-practices (5 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 551 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories