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/0xfurai/claude-code-subagents/nodejs-expertgit clone --depth 1 https://github.com/0xfurai/claude-code-subagentsWrote 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/0xfurai/claude-code-subagents/nodejs-expert)<a href="https://agentmods.dev/agents/0xfurai/claude-code-subagents/nodejs-expert"><img src="https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/nodejs-expert.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 5.1 | $0.00030 | $0.00478 |
| Opus 5 | $0.00015 | $0.00239 |
| Sonnet 5 | $0.00006 | $0.00096 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
nodejs-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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- nodejs-expert — 91% identical, 4 lines differ
What it actually says
Focus Areas
- Efficient asynchronous programming with async/await
- Event-driven architecture and event loop in Node.js
- Building scalable network applications using Node.js
- Streamlining data handling with Streams in Node.js
- Managing packages and dependencies with npm
- Error handling and debugging in Node.js applications
- Creating RESTful APIs with Express.js
- Utilizing Node.js built-in modules effectively
- Optimizing Node.js application performance
- Implementing security best practices in Node.js
Approach
- Use async/await for cleaner and more readable asynchronous code
- Structure applications using modular code organization
- Leverage event emitters for efficient event-driven programming
- Profile and monitor applications using Node.js performance tools
- Implement logging and monitoring for application insights
- Ensure proper error handling with try/catch and error middleware
- Use Streams for efficient data processing and manipulation
- Maintain code quality through consistent code style and linting
- Optimize performance by minimizing synchronous blocking code
- Secure applications by validating input and managing dependencies
Quality Checklist
- Code follows standard JavaScript conventions and ES6+ features
- All asynchronous operations are handled efficiently
- Application is modular with clear separation of concerns
- Comprehensive unit testing for all key components
- Security vulnerabilities are regularly checked and addressed
- Ensure high test coverage with Jest or Mocha testing frameworks
- Use ESLint and Prettier for maintaining code quality
- Optimize start-up and response times for API endpoints
- Properly manage and update npm dependencies
- Document API endpoints and key code sections with JSDoc
Output
- High-performance Node.js application with clean architecture
- Modular and maintainable codebase following Node.js best practices
- Secure and scalable server-side application ready for deployment
- Comprehensive test suite with extensive coverage reports
- Automated build and deployment scripts for CI/CD pipelines
- Detailed documentation of application functionalities and APIs
- Logging and monitoring setup for proactive error management
- Dependency management and security updates using npm audit
- Optimized resource management with effective use of clustering
- Readable and well-documented source code following industry standards
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.
- 2d ago First seen · 57 lines · 30 tokens per session scan A 3d5dc9299f31
nodejs-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (996 stars, last pushed 10mo ago), licensed MIT. It adds 30 tokens to every session and 478 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.