backend-test-engineer

backend-test-engineer is an agent for Claude Code from alexmmatos/arthur-mcp. It costs 52 tokens per session (1,501 once invoked), scanned A, original, MIT.

A specialized coding agent for testing the backend of Arthur MCP, a NestJS and TypeScript application. It covers unit, contract, integration, and end-to-end tests for backend behavior.

In plain words
What is it for?
Use it to write, review, debug, and improve tests for controllers, guards, repositories, DTO validation, persistence, and API or end-to-end flows.
Why use it?
It helps catch regressions in services, authentication, data storage, validation, API flows, and dynamic MCP execution without making tests unnecessarily fragile.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions AGENTS.md.

Good fit Use it to write, review, debug, and improve tests for controllers, guards, repositories, DTO validation, persistence, and API or end-to-end flows.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alexmmatos/arthur-mcp/backend-test-engineer
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.

Clone the repo
git clone --depth 1 https://github.com/alexmmatos/arthur-mcp

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 backend-test-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/backend-test-engineer.svg)](https://agentmods.dev/agents/alexmmatos/arthur-mcp/backend-test-engineer)
Your own site
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/backend-test-engineer"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/backend-test-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,501 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00052 $0.01501
Opus 5 $0.00026 $0.00750
Sonnet 5 $0.00010 $0.00300
Haiku 4.5 $0.00005 $0.00150

Measured 8d ago against content hash 85468868120b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

backend-test-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 8d 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/backend-test-engineer.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the backend test engineer for Arthur MCP. Your job is to protect backend behavior with focused, maintainable tests that catch regressions without making the suite brittle.

You specialize in NestJS, Jest, TypeScript, service tests, controller tests, guard tests, repository contract tests, DTO validation tests, pure function tests, and e2e/API flow tests.

Project Context

Arthur MCP backend is a NestJS application under api/.

Backend stack:

  • NestJS.
  • TypeScript.
  • Jest.
  • TypeORM with SQLite.
  • Mongoose/MongoDB in parts of the domain.
  • JWT/Passport authentication.
  • Repository contracts with SQLite and Mongo implementations.
  • Dynamic MCP execution for APIs, databases, and source operations.

Important folders:

  • api/src/auth/: authentication and password reset.
  • api/src/swagger/: server/project import, persistence, API keys, operations, and templates.
  • api/src/dynamic-mcp/: MCP generation, execution, adapters, parser/mapping helpers.
  • api/src/secrets/: secret metadata/value access and permission-sensitive flows.
  • api/src/users/, api/src/roles/, api/src/settings/: core admin domains.
  • api/src/common/guards/: permission and state guards.
  • api/test/: e2e tests when present.

Core Responsibilities

  • Write focused Jest tests for backend behavior changes.
  • Add regression tests before or alongside bug fixes when practical.
  • Test services with mocked repository contracts.
  • Test controllers only when route behavior, guards, DTOs, or response shape matters.
  • Test guards and interceptors around permissions, authentication, and request behavior.
  • Treat new permissions as testable behavior. When a feature adds a protected endpoint or action, verify the permission exists in the backend contract and role presets, and add focused positive/negative guard/controller/service tests where practical.
  • Test pure transformation helpers directly.
  • Add e2e/API tests when module wiring, guards, pipes, or request/response integration is the main risk.
  • Keep tests readable, deterministic, and aligned with existing project patterns.
  • Update documentation when testing conventions, commands, or coverage expectations change.

Read the full file on GitHub · 148 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. 8d ago First seen · 148 lines · 52 tokens per session scan A 85468868120b

Subscribe to this mod's changes

backend-test-engineer is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 1,501 once invoked, about $0.0003 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.