typescript-engineer

typescript-engineer is a skill for Claude Code, Codex from vosslab/vosslab-skills. It costs 56 tokens per session (3,277 once invoked), scanned A, original, MIT.

A TypeScript engineering guide for diagnosing compiler errors and designing clear, strict types. TypeScript is JavaScript with rules that describe what data and functions may contain.

In plain words
What is it for?
Use it for generics, conditional and mapped types, utility and branded types, function overloads, type declarations, module boundaries, and type-safety reviews.
Why use it?
It helps remove unsafe values such as `any` and prevents type problems from spreading across modules. It also gives structure to advanced type designs and strict refactors.

Skill for Claude CodeCodex

Part of the vosslab-skills plugin — 42 skills, 14 agents shipped together

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/vosslab/vosslab-skills/typescript-engineer
Any agent
npx skills add vosslab/vosslab-skills --skill typescript-engineer
Clone the repo
git clone --depth 1 https://github.com/vosslab/vosslab-skills

Made for: Claude Code, Codex.

Or install vosslab-skills, the plugin that ships this one along with the rest of its 42 skills, 14 agents.

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-engineer

README.md
[![agentmods](https://agentmods.dev/badge/skills/vosslab/vosslab-skills/typescript-engineer.svg)](https://agentmods.dev/skills/vosslab/vosslab-skills/typescript-engineer)
Your own site
<a href="https://agentmods.dev/skills/vosslab/vosslab-skills/typescript-engineer"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/typescript-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,277 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 $0.00056 $0.03277
Opus 5 $0.00028 $0.01639
Sonnet 5 $0.00011 $0.00655
Haiku 4.5 $0.00006 $0.00328

Measured 5d ago against content hash 3d84d2179894, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

typescript-engineer 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 5d 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.

skills/experts/typescript-engineer/SKILL.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TypeScript Engineer

Overview

Use this skill for type-level design, module-boundary type ownership, compiler-error diagnosis, and strict-safety refactoring in TypeScript. Route non-trivial work to the focused rule files in references/; do not answer from SKILL.md alone when the request involves advanced type behavior or shared type design.

Before any nontrivial repo work, read the target repo's AGENTS.md and CLAUDE.md overrides if they exist, then inspect the repo-local docs/TYPESCRIPT_STYLE.md or equivalent TypeScript instructions. The consumer repos are the source of truth for command front doors and local exceptions.

Design philosophy

  • Keep one responsibility per file.
  • Prefer small type modules with a single purpose over broad shared type dumping grounds.
  • Split runtime behavior, runtime validation, and type-level helpers into separate files when they change for different reasons.
  • Co-locate private helper types with the implementation that uses them.
  • Promote a type to a shared file only after multiple modules need the same contract.
  • Export stable contracts, not incidental implementation helper types.
  • Treat API, storage, validation, and domain shapes as separate owners unless the repo proves they change together. For single-domain projects (browser games, CLIs, simple libraries) where some of those owners do not exist, fall back to feature-area boundaries inside the domain.
  • Zero unchecked cast: as is permitted only inside a brand constructor, a type-guard return, or a documented boundary adapter. Never as a fix for a compiler error.
  • Keep shared guidance narrow. When a consumer repo intentionally diverges, document the exception instead of flattening it into the shared rule.

When to use

  • Untangle TypeScript compiler errors.
  • Eliminate any, unsafe unknown handling, or unchecked casts.
  • Design generics, conditional types, mapped types, template literal types, or branded types.
  • Design shared contracts, DTOs, schema-derived types, domain models, or public type APIs.
  • Refactor a file or module toward stricter compile-time safety without changing runtime behavior.
  • Explain a TypeScript type-system concept with concrete before and after examples.
  • Validate production refactors with tsc --noEmit and type-level tests.
  • Follow the repo's shell-script front doors first: ./check_codebase.sh, ./build_github_pages.sh, ./run_web_server.sh, and ./run_playwright_tests.sh. Many repos also mirror these with npm run check, build, serve, and test:playwright, but the shell scripts remain the interface.
  • Run repo Python helpers through source source_me.sh && python3 ... when the target repo uses the shared Python environment. Do not assume a bare python3 shell.
  • Resolve a narrow in-flight type contract during a parallel game build (invoked by a coding subagent, not a manager). One bounded question -- typically a single shared type, brand, or boundary shape -- and a typed stub the caller can import. Not a full audit; see html-game-parallel-builder for the wrapper that triggers this case.

Read the full file on GitHub · 251 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. 5d ago First seen · 251 lines · 56 tokens per session scan A 3d84d2179894

Subscribe to this mod's changes

typescript-engineer is a skill published in the GitHub repository vosslab/vosslab-skills (2 stars, last pushed 9d ago), licensed MIT. It adds 56 tokens to every session and 3,277 once invoked, about $0.0003 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 skills, from other repositories

lint-js

Lint JS/TS code only. Use before opening a PR when only JavaScript or TypeScript files were changed (no Rust).

denoland/deno · 29 tokens

no-bare-casts

Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.

prisma/orm · 52 tokens

dd-code-generation

Use pup CLI for immediate Datadog operations or generate code for integration into applications.

DataDog/pup · 16 tokens

migrate-better-result-3

Migrate a TypeScript codebase from better-result 2.x to 3.0. Use when upgrading better-result across the TaggedError syntax, removed Result serialization helpers, recovery inference, matching, or retry APIs.

dmmulroy/better-result · 52 tokens

fast-typescript-check

Keep www-sacred's TypeScript fast to type-check and fast to run. Use when touching the ASCII/canvas animation components (the only real per-frame code here), tightening type-check wall-clock, or auditing a change for runtime or compiler regressions. Scoped to this repo — a React 19 / Next.js 16 component library plus…

internet-development/www-sacred · 84 tokens

typescript-magician

Designs complex generic types, refactors any types to strict alternatives, creates type guards and utility types, and resolves TypeScript compiler errors. Use when the user asks about TypeScript (TS) types, generics, type inference, type guards, removing any types, strict typing, type errors, infer, extends…

mcollina/skills · 108 tokens