test-engineer

test-engineer is a skill for Claude Code, Codex from Aizaz-Noor/Agent-Startup-Skills. It costs 49 tokens per session (463 once invoked), scanned A, original, MIT.

A quality-assurance guide that creates automated unit tests, integration tests, and edge-case checks for software.

In plain words
What is it for?
Use it after implementation or when you need test coverage for business logic, API endpoints, unauthorized access, boundary values, and unusual inputs.
Why use it?
It checks both individual functions and larger request-to-response flows, including invalid input, missing authentication, limits, duplicates, and empty data.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it after implementation or when you need test coverage for business logic, API endpoints, unauthorized access, boundary values, and unusual inputs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aizaz-noor/agent-startup-skills/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.

Any agent
npx skills add Aizaz-Noor/Agent-Startup-Skills --skill test-engineer
Clone the repo
git clone --depth 1 https://github.com/Aizaz-Noor/Agent-Startup-Skills

Made for: Claude Code, Codex.

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 test-engineer

README.md
[![agentmods](https://agentmods.dev/badge/skills/aizaz-noor/agent-startup-skills/test-engineer/github.svg)](https://agentmods.dev/skills/aizaz-noor/agent-startup-skills/test-engineer)
Your own site
<a href="https://agentmods.dev/skills/aizaz-noor/agent-startup-skills/test-engineer"><img src="https://agentmods.dev/badge/skills/aizaz-noor/agent-startup-skills/test-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 test-engineer

Your own site · 80×15
<a href="https://agentmods.dev/skills/aizaz-noor/agent-startup-skills/test-engineer"><img src="https://agentmods.dev/badge/skills/aizaz-noor/agent-startup-skills/test-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 463 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 $0.00049 $0.00463
Opus 5 $0.00024 $0.00231
Sonnet 5 $0.00010 $0.00093
Haiku 4.5 $0.00005 $0.00046

Measured 10d ago against content hash a225c549b6a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

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 10d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/test-engineer/SKILL.md · 65 lines

What it actually says

Test Engineer — Quality Assurance Agent

Purpose

Ensure the codebase works correctly by writing automated tests and identifying edge cases that the Coder may have missed.

When to Use

  • After the codebase is implemented
  • When the user asks for test coverage
  • Before security audit (Phase 7 of SaaS Accelerator)

Process

Step 1: Test Strategy

Define what to test:

  • Unit Tests: Individual functions and utilities
  • Integration Tests: API endpoints (request → response)
  • Edge Cases: Empty inputs, boundary values, unauthorized access

Step 2: Unit Tests

For each business logic function:

  • Test the happy path (expected inputs → expected outputs)
  • Test with invalid inputs (null, empty, wrong type)
  • Test boundary values (min/max limits)

Step 3: API Integration Tests

For each API endpoint:

  • Test successful request (correct status code and response body)
  • Test with missing required fields (expect 400)
  • Test without authentication on protected routes (expect 401)
  • Test with invalid data types (expect 422)

Step 4: Edge Case Identification

Systematically check:

  • What happens with an empty database?
  • What happens with duplicate entries?
  • What happens with very long strings?
  • What happens with concurrent requests?
  • What happens when an external service is unavailable?

Step 5: Test Runner Configuration

Generate the test runner config file (e.g., jest.config.js, pytest.ini) and a test run command in package.json scripts.

Output

  • Test files organized in a tests/ directory
  • testing_plan.md with coverage summary
  • Manual test checklist for things that cannot be automated

Exit Criteria

  • Every API endpoint has at least one happy-path test
  • Every core business logic function has unit tests
  • At least 5 edge cases are explicitly tested
  • Test runner is configured and documented
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. 10d ago First seen · 65 lines · 49 tokens per session scan A a225c549b6a8

Subscribe to this mod's changes

test-engineer is a skill published in the GitHub repository Aizaz-Noor/Agent-Startup-Skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 463 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 2026-08-31.

Related

Other skills, from other repositories

unit-test

A Go testing workflow for writing unit tests: small tests that check individual functions or components. It supports table-driven cases, where many inputs and expected results are organised in one test, and subtests.

johnqtcg/awesome-skills · 100 tokens

fuzzing-test

A Go testing guide for generating fuzz tests, which repeatedly try varied inputs to find crashes and unexpected behavior. It first checks whether the code is suitable for fuzzing.

johnqtcg/awesome-skills · 74 tokens

ds-test

Universal test skill — generate, update, run, and fix tests for any stack. Use when writing, repairing, or running tests, or improving coverage.

sungurerdim/dev-skills · 34 tokens

unit-test-architect

Comprehensive unit testing patterns, mock/stub usages, and edge-case scenario coverage. / TR: Kapsamlı birim (unit) testleri, mock/stub kullanımları ve edge-case (uç durum) senaryoları yazma becerisi.

GktuOktay/ai-skills · 60 tokens

ds-build

Plan executor — take an issue, a specs/{feature}/tasks.md, or a plain request and implement it unit by unit with a verify signal per unit, red-proven tests, budgeted backtracking, and a code-proven close. Use when the plan exists and the work is to be done, not planned.

sungurerdim/dev-skills · 68 tokens

test-orchestrator

QA & testing orchestrator managing unit tests, E2E user scenarios, load testing, and performance benchmarks. / TR: Kapsamlı test stratejileri, birim testleri (unit), uçtan uca testler (E2E), performans ve yük testlerini yöneten ana orkestratör.

GktuOktay/ai-skills · 71 tokens