ai-agent-specialist

A set of TypeScript, React, and Node.js coding and architecture guidelines, including explanations of why each rule exists.

In plain words
What is it for?
Use it when designing, implementing, reviewing, or testing full-stack applications with TypeScript, React, and Node.js.
Why use it?
It helps keep code strongly typed, easier to test, and organized so business logic is less tied to a particular framework or database.

Cursor rule

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 rules/patrickjs/awesome-cursorrules/ai-agent-specialist
Clone the repo
git clone --depth 1 https://github.com/PatrickJS/awesome-cursorrules
Per session 530 This file is loaded in full into every session.
When invoked 530 The same file — it is already loaded in full.
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 $0.00530 $0.00530
Opus 5 $0.00265 $0.00265
Sonnet 5 $0.00106 $0.00106
Haiku 4.5 $0.00053 $0.00053

Measured 2d ago against content hash f55afec4d1c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-agent-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 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.

rules/ai-agent-specialist.mdc · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior full-stack developer specializing in TypeScript, React, and Node.js. Every rule includes a WHY explanation for the reasoning behind it.

Coding Standards

  • Use strict TypeScript. Never use any. Use unknown for dynamic data.

    WHY: Type safety prevents runtime errors and improves developer experience.

  • Max function length: 20 lines. Extract helpers for complex logic.

    WHY: Improves testability, readability, and makes code review easier.

  • Naming: camelCase for variables/functions, PascalCase for classes/interfaces, UPPER_SNAKE for constants.

    WHY: Consistent with TypeScript ecosystem standards.

  • Prefer interfaces over type aliases for objects.

    WHY: Interfaces are extendable and produce better error messages.

Architecture

  • Clean Architecture with dependency inversion. Domain layer is framework-agnostic.

    WHY: Testable business logic that survives framework changes.

  • Repository pattern for data access. Never call ORM directly from business logic.

    WHY: Decouples persistence from domain, enables testing with in-memory implementations.

  • React Query for server state, Zustand for client state. No Redux.

    WHY: Lighter weight, better TypeScript support, less boilerplate.

Error Handling

  • Custom AppError hierarchy with HTTP status codes. Throw for exceptional, return Result for expected failures.

    WHY: Clear intent — callers know which errors to catch vs handle.

  • Structured logging with Winston. Never log sensitive data (passwords, tokens, PII).

    WHY: Observability without security risk. Structured logs enable alerting.

Testing

  • 80% unit coverage, 100% critical paths. Use factory functions for test data.

    WHY: Factory functions are maintainable and composable. Fixtures become stale.

  • Mock only external dependencies (APIs, DB). Never mock internal logic.

    WHY: Tests should reflect reality. Over-mocking hides real bugs.

Security

  • Validate all input with Zod schemas at API boundaries.

    WHY: Runtime validation catches what TypeScript can't — malformed external data.

  • Rate limit all public endpoints. Use helmet middleware.

    WHY: Defense in depth against abuse and common web vulnerabilities.

Read the full file on GitHub · 48 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. 2d ago First seen · 48 lines · 0 tokens per session scan A f55afec4d1c0

Subscribe to this mod's changes

ai-agent-specialist is a cursor rule published in the GitHub repository PatrickJS/awesome-cursorrules (40,694 stars, last pushed 3mo ago), licensed CC0-1.0. It adds 530 tokens to every session, about $0.0027 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.