typescript-expert

typescript-expert is a skill for Claude Code, Codex from biggora/claude-plugins-registry. It costs 61 tokens per session (1,217 once invoked), scanned A, original, MIT.

TypeScript-specific guidance for designing types, reading compiler errors, configuring projects, generating declarations, moving JavaScript code to TypeScript, and upgrading versions.

In plain words
What is it for?
Use it when TypeScript rules or tooling are central to the task, including tsconfig settings, module resolution, declaration output, compiler diagnostics, JavaScript migration, and version upgrades.
Why use it?
It helps diagnose the TypeScript compiler actually used by a project and fix the earliest underlying problem without silently changing tools or runtime behaviour.

Skill for Claude CodeCodex

Part of the project-delivery-orchestrator plugin — 34 skills, 1 command, 5 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/biggora/claude-plugins-registry/typescript-expert
Any agent
npx skills add biggora/claude-plugins-registry --skill typescript-expert
Clone the repo
git clone --depth 1 https://github.com/biggora/claude-plugins-registry

Made for: Claude Code, Codex.

Or install project-delivery-orchestrator, the plugin that ships this one along with the rest of its 34 skills, 1 command, 5 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-expert

README.md
[![agentmods](https://agentmods.dev/badge/skills/biggora/claude-plugins-registry/typescript-expert.svg)](https://agentmods.dev/skills/biggora/claude-plugins-registry/typescript-expert)
Your own site
<a href="https://agentmods.dev/skills/biggora/claude-plugins-registry/typescript-expert"><img src="https://agentmods.dev/badge/skills/biggora/claude-plugins-registry/typescript-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,217 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 5.1 $0.00061 $0.01217
Opus 5 $0.00030 $0.00609
Sonnet 5 $0.00012 $0.00243
Haiku 4.5 $0.00006 $0.00122

Measured 5d ago against content hash 85d8077d39c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 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.

src/skills/typescript-expert/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TypeScript Expert

Use the project's installed TypeScript version and runtime/toolchain constraints as the source of truth. This guidance was checked against TypeScript 7.0.2, the stable latest release on 2026-08-29. When “latest” matters, verify the current stable tag and official release notes instead of relying on this date.

Canonical sources:

Working Method

  1. Inspect package.json, the lockfile, all applicable tsconfig*.json files and extends chains before recommending code or configuration.
  2. Determine the actual compiler used by the failing command. Framework checkers such as vue-tsc, svelte-check, Angular, Astro, and MDX tooling may embed or constrain a different TypeScript version.
  3. Reproduce the diagnostic with the project's existing script and local dependency. Do not silently download or substitute the newest compiler.
  4. Fix the earliest root cause with the smallest runtime-preserving change. Re-run the same command; use a focused compile or type test only as additional evidence.
  5. Report the compiler version, command, result, and any remaining baseline or compatibility limitation.

When the user asks for an upgrade, read modern TypeScript releases before editing. TypeScript 7 is the current stable CLI/compiler, but it does not yet expose a stable programmatic API and is not a drop-in replacement for every tool that embeds TypeScript. Keep compatible tooling on TypeScript 6 where the official 7.0 guidance requires it.

Decision Rules

  • Prefer inference for local values; annotate public boundaries when the annotation documents intent or catches implementation drift.
  • Accept untrusted values as unknown, validate or narrow them at runtime, and keep the validated type aligned with the runtime check.
  • Prefer discriminated unions for states, overloads for a small finite call surface, and generics only when they preserve a real relationship between inputs and outputs.
  • Treat as, non-null assertions, any, @ts-ignore, and broad ambient declarations as evidence to investigate. Use a narrow assertion only when an invariant is established outside the type system and explain that invariant.
  • Prefer @ts-expect-error over @ts-ignore only for an intentional, tested negative case or documented upstream limitation. Do not use either to make an ordinary type-check pass.
  • Do not change runtime behavior merely to satisfy a type unless the existing runtime behavior is itself the bug.
  • Do not recommend compiler flags in isolation. Choose module, moduleResolution, target, lib, emit settings, and file selection as one configuration for the actual runtime or bundler.
  • Preserve framework-generated options and project references. Do not replace an existing tsconfig with a generic template.
  • For libraries, validate declaration emit and consumer module resolution, not only the source project's noEmit check.
  • For complex types, optimize for readable diagnostics and bounded compiler work; a simpler public type is often better than a perfectly computed one.

Read the full file on GitHub · 72 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 · 72 lines · 61 tokens per session scan A 85d8077d39c6

Subscribe to this mod's changes

typescript-expert is a skill published in the GitHub repository biggora/claude-plugins-registry (2 stars, last pushed 7d ago), licensed MIT. It adds 61 tokens to every session and 1,217 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