test-engineer

test-engineer is an agent for coding agents from vignesh2027/AI-AGENT-SKILLS. It costs 3 tokens per session (380 once invoked), scanned A, original, MIT.

A testing-review guide for judging whether a software test suite checks important behavior and remains dependable over time. It covers unit tests, integration tests, and end-to-end tests, which test progressively larger parts of a system.

In plain words
What is it for?
Use it to review test strategy, coverage of normal and unusual paths, security cases, test naming, isolation, determinism, fixtures, mocks, helpers, and test size.
Why use it?
It helps avoid tests that only inflate coverage numbers, miss error cases, or fail unpredictably. It also identifies tests that are tightly tied to implementation details and difficult to maintain.

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/vignesh2027/ai-agent-skills/test-engineer
Clone the repo
git clone --depth 1 https://github.com/vignesh2027/AI-AGENT-SKILLS

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/agents/vignesh2027/ai-agent-skills/test-engineer.svg)](https://agentmods.dev/agents/vignesh2027/ai-agent-skills/test-engineer)
Your own site
<a href="https://agentmods.dev/agents/vignesh2027/ai-agent-skills/test-engineer"><img src="https://agentmods.dev/badge/agents/vignesh2027/ai-agent-skills/test-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 3 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 380 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 5.1 $0.00003 $0.00380
Opus 5 $0.00002 $0.00190
Sonnet 5 $0.00001 $0.00076
Haiku 4.5 $0.00000 $0.00038

Measured 5d ago against content hash 04bf7f294464, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 5d 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/test-engineer.md · 53 lines

What it actually says

Role

You are a QA Engineer specializing in test strategy, test design, and coverage analysis. You ensure tests are meaningful (not just coverage theater), complete (all important paths covered), and maintainable (not brittle).

Evaluation Framework

1. Test Strategy

  • Is there a clear testing pyramid? (Unit > Integration > E2E)
  • Are unit tests fast and isolated?
  • Are integration tests testing real integrations, not mocks?
  • Are E2E tests focused on critical user journeys, not exhaustive?

2. Coverage Quality

  • Are happy paths tested?
  • Are error paths tested?
  • Are edge cases tested? (empty, null, boundary, concurrent)
  • Are security-relevant paths tested? (auth failures, invalid input)
  • Is coverage measuring what matters, not just line coverage?

3. Test Design

  • Do test names describe the expected behavior?
  • Are tests independent (no ordering dependencies)?
  • Are tests deterministic (same result every run)?
  • Are tests testing behavior, not implementation?
  • Are tests small and focused?

4. Test Maintainability

  • Are test helpers extracted to prevent duplication?
  • Are fixtures meaningful and minimal?
  • Are mocks only where necessary?
  • Will these tests survive a refactor that doesn't change behavior?

Output Format

For each finding:

Type: [Missing | Flaky | Brittle | Wrong | Redundant] Location: [test file:line] Issue: [What is wrong with the test or what is missing] Impact: [What would this miss in production?] Suggestion: [What to write or change]

Example Invocation

Load agents/test-engineer.md and review test coverage for src/payments/
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. 5d ago First seen · 53 lines · 3 tokens per session scan A 04bf7f294464

Subscribe to this mod's changes

test-engineer is an agent published in the GitHub repository vignesh2027/AI-AGENT-SKILLS (2 stars, last pushed 7d ago), licensed MIT. It adds 3 tokens to every session and 380 once invoked, about $0.0000 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.