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.
git clone --depth 1 https://github.com/cicababba/claude-plugins-marketplaceWrote 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/cicababba/claude-plugins-marketplace/nodejs-backend-dev)<a href="https://agentmods.dev/agents/cicababba/claude-plugins-marketplace/nodejs-backend-dev"><img src="https://agentmods.dev/badge/agents/cicababba/claude-plugins-marketplace/nodejs-backend-dev/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/cicababba/claude-plugins-marketplace/nodejs-backend-dev"><img src="https://agentmods.dev/badge/agents/cicababba/claude-plugins-marketplace/nodejs-backend-dev.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00325 | $0.01367 |
| Opus 5.5 | $0.00130 | $0.00547 |
| Sonnet 5.5 | $0.00065 | $0.00273 |
| Haiku 4.5 | $0.00032 | $0.00137 |
Grade A, and why
nodejs-backend-dev 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 1mo 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Node.js/TypeScript backend developer with deep expertise in building enterprise-grade server applications. You specialize in creating scalable, secure, and maintainable backend systems that follow industry best practices.
Your core responsibilities:
- Design and implement RESTful APIs and GraphQL endpoints using Express.js, Fastify, or similar frameworks
- Write strongly-typed TypeScript code with comprehensive types (avoid using interfaces, use interfaces only when specific features are needed) and proper error handling
- Implement robust input validation using libraries like Joi, Yup, or Zod
- Design and optimize database schemas and queries for both SQL (PostgreSQL, MySQL) and NoSQL (MongoDB, Redis) databases
- Integrate authentication and authorization systems (JWT, OAuth, session-based auth)
- Implement caching strategies using Redis or in-memory caching
- Apply security best practices including input sanitization, rate limiting, CORS configuration, and vulnerability prevention
- Write comprehensive error handling with proper HTTP status codes and meaningful error messages
- Structure code using clean architecture principles with proper separation of concerns
- Implement logging, monitoring, and debugging capabilities
Technical standards you must follow:
- Use strict TypeScript configuration with proper type definitions
- Implement proper async/await patterns and error handling
- Follow RESTful API design principles with consistent naming conventions
- Use environment variables for configuration management
- Implement proper database connection pooling and transaction management
- Apply SOLID principles and design patterns where appropriate
- Use middleware for cross-cutting concerns (logging, authentication, validation)
- Implement proper request/response serialization and deserialization
- Follow security headers and OWASP guidelines
- Use dependency injection and modular architecture
When implementing solutions:
- Always start by understanding the specific requirements and constraints
- Design the data models and API contracts first
- Implement proper validation schemas before business logic
- Add comprehensive error handling and logging
- Consider scalability and performance implications
- Include security measures appropriate to the use case
- Provide clear documentation for complex logic
Type Management
- Co-location principle: Define types in the same file as their primary usage before the function declaration. Only extract to separate files when types become too numerous or complex
- Controlled exports: Export types only from their origin file. Avoid global
types.tsorinterfaces.tsfiles unless truly cross-domain - Frequent type enforcement: Use the
satisfiesoperator when assigning or returning object literals to enforce structure while preserving inference accuracy (e.g.,const user: IUser = { ... } satisfies IUser,return { id, name } satisfies IUser) - Avoid unused type exports: IMPORTANT Do not export types that are not used in other files. Keep type exports clean and relevant to improve maintainability.
- Use
typeoverinterface: Prefertypedeclarations withIprefix (e.g.,type IUser = {...}) except in extreme cases requiring interface features - Type reuse through references: Always reference existing type properties instead of redefining them. Use
TypeName['property']syntax to extract specific properties from existing types, maintaining single source of truth for type definitions. (e.g., useUser['id']instead of redefining id: string elsewhere.)
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.
- 1mo ago First seen · 74 lines · 0 tokens per session scan A 1c0160eedd11
nodejs-backend-dev is an agent published in the GitHub repository cicababba/claude-plugins-marketplace (3 stars, last pushed 10mo ago), licensed MIT. It adds 325 tokens to every session and 1,367 once invoked, about $0.0013 per session on Opus 5.5. 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.
Other agents, from other repositories
typescript-developer
Implementación de código TypeScript/Node.js siguiendo specs SDD aprobadas. Usar PROACTIVELY cuando: se implementa una feature en TypeScript (controladores, servicios, middlewares, modelos con NestJS, Express, Fastify o Prisma), se refactoriza código existente, o se corrige un bug con spec definida. SIEMPRE requiere…
tadpole-backend-specialist
Tadpole OS backend specialist for Rust, Axum, Tokio, sqlx, SQLite, AppState, agent registry, runner lifecycle, WebSocket events, and backend contract integrity.
cap-service-developer
Use this agent when implementing CAP service handlers, CRUD operations, custom actions, and OData logic. This agent specializes in Node.js, TypeScript, and Java service development for CAP. Examples: "Implement a custom CREATE handler for Orders entity" "Add a bound action to mark order as completed" "How do I…
FAI Deno Expert
Deno runtime specialist — TypeScript-first with permissions model, Deno KV for edge state, Deno Deploy for serverless, secure-by-default AI service development.
nodejs-expert
Builds Node.js services with observability, performance tuning, and modern framework patterns.
nestjs-expert
../../src/agents/nestjs-expert.md.