ts-types

A command that creates or improves TypeScript descriptions of data and code, such as object shapes, API responses, JSON, database schemas, and library interfaces.

In plain words
What is it for?
Use it to infer function and object types from JavaScript, model JSON or API responses, convert database schemas, and create types for libraries without existing type definitions.
Why use it?
It reduces the manual work of describing what values look like and helps code use data with clearer type checks.

Command

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 commands/andronics/claude-plugin-typescript-pro/ts-types
Clone the repo
git clone --depth 1 https://github.com/andronics/claude-plugin-typescript-pro
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 707 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 $0.00015 $0.00707
Opus 5 $0.00008 $0.00353
Sonnet 5 $0.00003 $0.00141
Haiku 4.5 $0.00002 $0.00071

Measured 2d ago against content hash caf205d95cfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ts-types 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.

commands/ts-types.md · 109 lines

What it actually says

Generate and refine TypeScript types from various sources:

  1. Identify Type Source

    • Determine what needs types:
      • JavaScript code to be typed
      • API response to model
      • JSON data to type
      • Database schema to represent
      • External library without @types
      • Props interface from usage
    • Source can be from: $ARGUMENTS, current file, or clipboard
  2. Generate Types from Different Sources

    From JavaScript Code:

    • Analyze JS function/class structure
    • Infer parameter types from usage
    • Determine return types
    • Generate interfaces for objects

    From Runtime Data:

    // Input: JSON response
    const response = {
      user: { id: 1, name: "Alice", email: "[email protected]" },
      posts: [{ id: 1, title: "Hello", published: true }]
    };
    
    // Generated:
    interface User {
      id: number;
      name: string;
      email: string;
    }
    
    interface Post {
      id: number;
      title: string;
      published: boolean;
    }
    
    interface Response {
      user: User;
      posts: Post[];
    }
    

    From API Documentation:

    • Parse OpenAPI/Swagger schemas
    • Generate types with proper optionality
    • Handle union types and discriminated unions
    • Create type-safe API client

    From Database Schema:

    • Convert SQL schema to TypeScript
    • Map SQL types to TS types
    • Handle nullable columns
    • Generate query result types
  3. Refine Existing Types

    • Make types more specific (string → literal union)
    • Add utility type usage (Partial, Pick, Omit)
    • Convert any to proper types
    • Add JSDoc documentation
    • Improve generic constraints
    • Use discriminated unions for state
  4. Generate Derived Types

    • Create input/output variants (CreateUser vs User)
    • Generate partial types for updates
    • Create picker types for specific use cases
    • Build form field types from domain types
  5. Add Type Guards

    • Generate runtime validation functions
    • Create is predicates for type narrowing
    • Add exhaustive checks for unions
    • Validate external data at boundaries
  6. Type Optimization

    • Simplify overly complex types
    • Extract reusable type aliases
    • Remove redundant type annotations
    • Use const assertions where appropriate
  7. Documentation

    • Add JSDoc comments to generated types
    • Document complex type parameters
    • Provide usage examples
    • Explain non-obvious type decisions
  8. Validation Integration

    • Suggest zod/yup schemas alongside types
    • Generate runtime validators from types
    • Ensure types and validators stay in sync

Examples:

  • /ts-types - Generate types for current file
  • /ts-types api-response.json - Generate from JSON file
  • /ts-types https://api.example.com/users - From API response
  • /ts-types refine - Improve existing types

The generated types will be type-safe, well-documented, and follow TypeScript best practices.

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 · 109 lines · 15 tokens per session scan A caf205d95cfa

Subscribe to this mod's changes

ts-types is a command published in the GitHub repository andronics/claude-plugin-typescript-pro (4 stars, last pushed 10mo ago), licensed MIT. It adds 15 tokens to every session and 707 once invoked, about $0.0001 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.