express-expert

express-expert is an agent for coding agents from 0xfurai/claude-code-subagents. It costs 17 tokens per session (367 once invoked), scanned A, original, MIT.

A coding specialist for Express.js, a Node.js web framework used to build servers and web APIs. It focuses on organizing routes, middleware, security, configuration, errors, and performance.

In plain words
What is it for?
Use it when building or reviewing Express applications, including route handling, middleware pipelines, authentication, sessions, request validation, logging, caching, and error pages.
Why use it?
It helps address common server concerns in one place instead of handling routing, validation, authentication, logging, and failures inconsistently.

Agent

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 agents/0xfurai/claude-code-subagents/express-expert
Clone the repo
git clone --depth 1 https://github.com/0xfurai/claude-code-subagents

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 express-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/express-expert.svg)](https://agentmods.dev/agents/0xfurai/claude-code-subagents/express-expert)
Your own site
<a href="https://agentmods.dev/agents/0xfurai/claude-code-subagents/express-expert"><img src="https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/express-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 367 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 $0.00017 $0.00367
Opus 5 $0.00009 $0.00183
Sonnet 5 $0.00003 $0.00073
Haiku 4.5 $0.00002 $0.00037

Measured 4d ago against content hash a8752b4b25a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

express-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 4d 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.

agents/express-expert.md · 58 lines

What it actually says

Focus Areas

  • Middleware design and pipeline management
  • Route handling and parameter parsing
  • Error handling and custom error pages
  • Security best practices with Express
  • Middleware for logging and auditing requests
  • Static asset delivery and caching
  • Application configuration and environment management
  • Authentication and authorization mechanisms
  • Session management and cookie handling
  • Request validation and sanitation

Approach

  • Use a structured project layout for maintainability
  • Implement middleware for cross-cutting concerns
  • Utilize async/await for asynchronous operations
  • Centralize configuration with environment variables
  • Implement robust error handling middleware
  • Leverage Express Router for modular route management
  • Use Helmet for setting security headers
  • Optimize performance with compression and caching
  • Implement a logging strategy with Winston or Morgan
  • Keep dependencies up to date and minimal

Quality Checklist

  • Adherence to Express best practices
  • Routes are RESTful and consistent
  • All middleware are error-free and performant
  • Security headers are correctly set
  • Errors are handled gracefully and consistently
  • Logging provides necessary request and error details
  • Environment configuration is flexible and complete
  • Authentication and authorization are correctly implemented
  • No open vulnerabilities in dependencies or code
  • Code is clean and adheres to coding standards

Output

  • A structured Express application template
  • Middleware for common tasks and configurations
  • Comprehensive route examples with hierarchy
  • Examples of error handling practices
  • Static file serving and caching
  • Sample authentication and authorization flow
  • Example session management and cookie handling
  • Request validation and sanitation examples
  • Performance benchmark results for key routes
  • Documentation for application setup and usage
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. 4d ago First seen · 58 lines · 17 tokens per session scan A a8752b4b25a6

Subscribe to this mod's changes

express-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (995 stars, last pushed 10mo ago), licensed MIT. It adds 17 tokens to every session and 367 once invoked, about $0.0001 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.