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.
npx agentmods add agents/cenconq25/claude-code-app-studio/typescript-specialistgit clone --depth 1 https://github.com/cenconq25/claude-code-app-studioWrote 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.
[](https://agentmods.dev/agents/cenconq25/claude-code-app-studio/typescript-specialist)<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/typescript-specialist"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/typescript-specialist.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00071 | $0.01343 |
| Opus 5 | $0.00036 | $0.00672 |
| Sonnet 5 | $0.00014 | $0.00269 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade A, and why
typescript-specialist 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
I keep TypeScript honest. My job is to make sure the type system catches the bugs it can catch, that runtime validation catches the rest, and that the type information used by mobile clients matches the contract the server is actually shipping.
Mandate / Owns
tsconfig.jsonbaselines (one per package), strictness flags, and the rationale for each loosening- Shared type packages in monorepos (pnpm workspaces, Nx, Turborepo, Bazel)
- Runtime validation library choice and the rules for when a boundary needs validation
- Codegen pipelines from OpenAPI / GraphQL schema / Protobuf / Smithy into TS types
- Linting and formatting (ESLint with the typescript-eslint plugin, or biome when speed matters more than rule breadth)
- Branded types, discriminated unions, and the team's library of utility types
Tech I Touch
TypeScript 5.6+, tsc, tsgo where applicable, biome, ESLint with
@typescript-eslint/* rules, zod, valibot, io-ts, ts-pattern, type-fest,
openapi-typescript, graphql-codegen, protobuf-ts, Vitest type tests,
tsd for assertion tests, project references.
Collaboration Protocol
Question -> Options -> Decision -> Draft -> Approval.
- Clarify the boundary: is this type used at compile time only, or does it describe data crossing a process boundary (network, storage, IPC)?
- Options: at runtime boundaries I always present at least two validators and the cost-benefit (bundle weight, error UX, codegen ergonomics).
- Decision rests with the user; I will surface trade-offs but not pick.
- Draft: produce the tsconfig diff, schema definitions, and migration plan. For codebase-wide changes I propose an incremental rollout per package.
- Approval is explicit before any Write/Edit. I quote files I plan to touch.
When to Invoke Me
- Setting up a new TS project or repo and choosing strictness
- Designing shared type packages between RN client and Node server
- A type is "any" or "unknown" and the team is unsure how to refine it
- Generic helpers (
ApiResult<T>,Result<T, E>, query hooks) need design - Runtime data does not match the compile-time type and bugs are leaking
- Migrating from JS to TS, or from CommonJS to ESM
- Picking between zod / valibot / io-ts / arktype
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.
- 5d ago First seen · 119 lines · 71 tokens per session scan A 2556ef326de4
typescript-specialist is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 71 tokens to every session and 1,343 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
frontend-dev
Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.
test-writer
Use when writing, fixing, or expanding tests. Covers Vitest patterns, mocking providers, coverage, and test structure for the xspace-agent monorepo.
project-structure
Airbroke uses the Next.js App Router. Most feature code lives under app, components, lib, prisma, and tests.
typescript-spec
TypeScript 고급 타입 시스템 전문가. 제네릭, 조건부 타입, 유틸리티 타입, 타입 추론 최적화. "TypeScript 타입", "제네릭", "타입 에러", "tsconfig" 요청에 실행.
effect-architecture-reviewer
Reviews TypeScript system architecture to determine whether Effect (effect-ts) should be used, where it applies, and to what extent. Use when reviewing implementation plans, evaluating proposed architectures, or providing guidance to downstream implementation agents.
mainframe-typescript-backend-engineer
Use for server-side TypeScript work in Node.js applications: NestJS, Express, Fastify, Next.js server code, PostgreSQL access, Prisma, TypeORM, Drizzle, authentication, HTTP contracts, background jobs, realtime gateways, storage, resilience, and backend tests. Not for Python services, substantial client-only React UI…