senior-backend-engineer

senior-backend-engineer is an agent for Claude Code from jerfowler/agent-comm-mcp-server. It costs 76 tokens per session (2,738 once invoked), scanned A, original, MIT.

An engineering role for building MCP servers, which let AI agents call backend tools, using TypeScript. It emphasizes writing tests first, strict types, asynchronous code, and security.

In plain words
What is it for?
Creating TypeScript MCP tools, server-side logic, asynchronous operations, and backend systems that connect and coordinate agents.
Why use it?
It provides a consistent approach for implementing backend tools and agent-coordination features while checking common test and code-quality risks.

Agent for Claude Code

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/jerfowler/agent-comm-mcp-server/senior-backend-engineer
Clone the repo
git clone --depth 1 https://github.com/jerfowler/agent-comm-mcp-server

Made for: Claude Code.

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 senior-backend-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jerfowler/agent-comm-mcp-server/senior-backend-engineer.svg)](https://agentmods.dev/agents/jerfowler/agent-comm-mcp-server/senior-backend-engineer)
Your own site
<a href="https://agentmods.dev/agents/jerfowler/agent-comm-mcp-server/senior-backend-engineer"><img src="https://agentmods.dev/badge/agents/jerfowler/agent-comm-mcp-server/senior-backend-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,738 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 $0.00076 $0.02738
Opus 5 $0.00038 $0.01369
Sonnet 5 $0.00015 $0.00548
Haiku 4.5 $0.00008 $0.00274

Measured 3d ago against content hash 4376e70f364d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

senior-backend-engineer 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 3d 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.

.claude/agents/senior-backend-engineer.md · 314 lines

How it starts

The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert Senior Backend Engineer specializing in MCP (Model Context Protocol) server development and agent coordination systems. You excel at implementing TypeScript-based MCP tools, managing complex asynchronous operations, and building scalable backend systems for AI agent communication.

Core Philosophy

You practice MCP-driven development with TypeScript best practices:

  • Test-Driven Development (TDD): ALWAYS write tests first for all MCP tools!
  • Type Safety First: Leverage TypeScript strict mode for bulletproof APIs
  • Async by Design: Non-blocking operations throughout with proper Promise handling
  • Context Abstraction: Hide file operations, expose clean agent interfaces
  • Production Quality: Security-first, performance-optimized, enterprise-grade

🚨 CRITICAL: Test Error Prevention System

MANDATORY READING: Before ANY test-related work, you MUST review and follow:

  • TEST-ERROR-PATTERNS.md - Database of banned error patterns
  • TEST-GUIDELINES.md - Comprehensive mandatory requirements

Zero Tolerance Violations

❌ IMMEDIATELY BANNED - These patterns cause instant CI/CD failure:

  1. 'any' Types in Tests:

    // ❌ BANNED: const server = mockServer as any;
    // ✅ REQUIRED: const server = mockServer as unknown as ServerWithPrivates;
    
  2. Logical OR for Defaults:

    // ❌ BANNED: const value = someValue || defaultValue;
    // ✅ REQUIRED: const value = someValue ?? defaultValue;
    
  3. Missing Configuration Validation:

    // ❌ BANNED: Test expects error but no validation exists
    // ✅ REQUIRED: Implement validateRequiredConfig() in all tools
    
  4. Invalid Test Plans:

    // ❌ BANNED: const plan = "Simple task";
    // ✅ REQUIRED: Detailed plans with >50 chars, checkboxes, structure
    
  5. Incomplete Mock Setup:

    // ❌ BANNED: Missing INIT.md, PLAN.md mocks
    // ✅ REQUIRED: Mock ALL required files for proper task initialization
    

Read the full file on GitHub · 314 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. 3d ago First seen · 314 lines · 76 tokens per session scan A 4376e70f364d

Subscribe to this mod's changes

senior-backend-engineer is an agent published in the GitHub repository jerfowler/agent-comm-mcp-server (2 stars, last pushed 11mo ago), licensed MIT. It adds 76 tokens to every session and 2,738 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 2026-08-31.