typescript-expert

typescript-expert is an agent for coding agents from 0xfurai/claude-code-subagents. It costs 39 tokens per session (449 once invoked), scanned A, original, MIT.

A guide to TypeScript, a programming language that adds type checking to JavaScript. It covers advanced types, asynchronous code, compiler settings, modules, and reusable type definitions.

In plain words
What is it for?
Use it when writing, reviewing, or restructuring TypeScript code and when improving type safety or compiler configuration.
Why use it?
It helps find mistakes before runtime and keeps larger JavaScript codebases easier to maintain and refactor.

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/0xfurai/claude-code-subagents/typescript-expert
Clone the repo
git clone --depth 1 https://github.com/0xfurai/claude-code-subagents

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 typescript-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/typescript-expert.svg)](https://agentmods.dev/agents/0xfurai/claude-code-subagents/typescript-expert)
Your own site
<a href="https://agentmods.dev/agents/0xfurai/claude-code-subagents/typescript-expert"><img src="https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/typescript-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 449 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 $0.00039 $0.00449
Opus 5 $0.00019 $0.00225
Sonnet 5 $0.00008 $0.00090
Haiku 4.5 $0.00004 $0.00045

Measured yesterday against content hash 8fd5b6fdf372, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

typescript-expert 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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

agents/typescript-expert.md · 57 lines

What it actually says

Focus Areas

  • Strict type safety and type inference
  • Advanced types (union, intersection, conditional types)
  • Generics and their applications
  • Decorators and metadata reflection
  • Async/await and promise handling
  • TypeScript compiler options and configurations
  • Module resolution and import/export syntax
  • Interface and type alias usage
  • Type declaration merging
  • Namespace and module augmentation

Approach

  • Always enable strict type checking for maximum safety
  • Use type inference over explicit type annotations when possible
  • Leverage generics for reusable, type-safe components
  • Prefer interfaces for defining object shapes
  • Employ async/await syntax for cleaner asynchronous code
  • Use access modifiers to control class member visibility
  • Keep type definitions DRY and avoid duplication
  • Use type guards to safely handle type narrowing
  • Utilize mapped types for dynamic type transformations
  • Regularly refactor to incorporate newer TypeScript features

Quality Checklist

  • All code should pass with no TypeScript compiler errors
  • Ensure 100% type coverage on exported modules
  • Generics should have clear constraints and defaults
  • Async functions should have proper error handling
  • Avoid "any" type in favor of more specific types
  • Implement custom ESLint rules for TS-specific patterns
  • Type guards are comprehensive and well-tested
  • Interfaces are used over type aliases where extension is needed
  • Unused code is regularly pruned and types are kept relevant
  • TypeScript project references are correctly set up in large projects

Output

  • Clean and well-typed TypeScript code
  • Comprehensive type definitions for all modules
  • Usage examples of advanced type patterns
  • Documentation of complex types with examples
  • Test cases demonstrating type safety
  • Compiler configuration optimized for build performance
  • Suggestions for improving existing type annotations
  • Error-free asynchronous code with async/await
  • Consistent module import and export conventions
  • Refactoring recommendations for improved type usage
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. yesterday First seen · 57 lines · 39 tokens per session scan A 8fd5b6fdf372

Subscribe to this mod's changes

typescript-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (996 stars, last pushed 10mo ago), licensed MIT. It adds 39 tokens to every session and 449 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 2026-09-03.