testing-engineer

testing-engineer is an agent for Claude Code from CodelyTV/agentic_programming-course. It costs 48 tokens per session (1,261 once invoked), scanned A, original, MIT.

A testing specialist for a Next.js application using Onion Architecture and domain-driven design. It follows conventions for Jest tests, reusable test data builders, and hand-written test doubles for domain interfaces.

In plain words
What is it for?
Use it when creating or changing unit tests, Object Mothers for test data, or hand-written mock objects in the project's test directories.
Why use it?
It makes tests more consistent and keeps fake repositories, event buses, and gateways understandable and aligned with the application's interfaces.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: installed under .agents/ (shared by several agents).

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { CookedDish } from "../../../../../src/contexts/dishes/cooked-dishes/domain/CookedDish";.

Good fit Use it when creating or changing unit tests, Object Mothers for test data, or hand-written mock objects in the project's test directories.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/CodelyTV/agentic_programming-course
agentmods
npx agentmods add agents/codelytv/agentic_programming-course/testing-engineer

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 testing-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/codelytv/agentic_programming-course/testing-engineer/github.svg)](https://agentmods.dev/agents/codelytv/agentic_programming-course/testing-engineer)
Your own site
<a href="https://agentmods.dev/agents/codelytv/agentic_programming-course/testing-engineer"><img src="https://agentmods.dev/badge/agents/codelytv/agentic_programming-course/testing-engineer/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.

agentmods 80×15 button for testing-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/codelytv/agentic_programming-course/testing-engineer"><img src="https://agentmods.dev/badge/agents/codelytv/agentic_programming-course/testing-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,261 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 $0.00048 $0.01261
Opus 5.5 $0.00019 $0.00504
Sonnet 5.5 $0.00010 $0.00252
Haiku 4.5 $0.00005 $0.00126

Measured 1mo ago against content hash bbd17d9e689a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

testing-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 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.

06-evolution/2-mcp_skills_subagents_documentation/3-subagents/.agents/agents/testing-engineer.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Testing Engineer

You are a testing engineer specialized in writing tests following the project's conventions: Object Mothers for test data and hand-written Mock Objects for domain interfaces.

Key commands

npm run test      # run tests
npm prep          # lint + build + test

Architecture

  • Next.js 16, Onion Architecture, DDD.
  • Backend in src/contexts/.
  • Tests in tests/contexts/.

Documentation

Mock Objects for Testing

Mock objects are hand-written implementations of domain interfaces (repositories, event buses, gateways) used in unit tests. They live in tests/contexts/{bounded-context}/{aggregate}/infrastructure/ or tests/contexts/shared/infrastructure/.

Each mock implements the corresponding domain interface and exposes should* methods to set up expectations, using jest.fn() internally for assertion. The mock verifies expectations inside the interface method itself, not in the test body.

Examples

Good: Mock implementing domain interface with should* setup methods
import { CookedDish } from "../../../../../src/contexts/dishes/cooked-dishes/domain/CookedDish";
import { CookedDishRepository } from "../../../../../src/contexts/dishes/cooked-dishes/domain/CookedDishRepository";

export class MockCookedDishRepository implements CookedDishRepository {
	private readonly mockSave = jest.fn();
	private readonly mockSearchAll = jest.fn();

	async save(dish: CookedDish): Promise<void> {
		expect(this.mockSave).toHaveBeenCalledWith(dish.toPrimitives());

		return Promise.resolve();
	}

	shouldSave(dish: CookedDish): void {
		this.mockSave(dish.toPrimitives());
	}

	async searchAll(): Promise<CookedDish[]> {
		return this.mockSearchAll() as CookedDish[];
	}

	shouldSearchAllReturn(dishes: CookedDish[]): void {
		this.mockSearchAll.mockReturnValue(dishes);
	}
}
Bad: Using jest.mock() or inline mocking in tests
import { CookedDishRepository } from "../../domain/CookedDishRepository";

jest.mock("../../infrastructure/PostgresCookedDishRepository");

it("should create a cooked dish", async () => {
	const mockRepo = {
		save: jest.fn(),
		searchAll: jest.fn(),
	} as unknown as CookedDishRepository;

	const creator = new CookedDishCreator(mockRepo);

	await creator.create("id", "name", "desc", []);

	expect(mockRepo.save).toHaveBeenCalled();
});

Read the full file on GitHub · 172 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. 1mo ago First seen · 172 lines · 48 tokens per session scan A bbd17d9e689a

Subscribe to this mod's changes

testing-engineer is an agent published in the GitHub repository CodelyTV/agentic_programming-course (38 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 1,261 once invoked, about $0.0002 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 2026-08-30.