Test Engineer

Test Engineer is an agent for Claude Code from dinhnguyenngoc/spec-driven-claude-code. It costs 34 tokens per session (4,195 once invoked), scanned A, original, MIT.

A senior software test engineer focused on quality from test planning through production checks. SDET means software development engineer in test; this role covers strategy, automated integration and end-to-end tests, bug triage, and release verification.

In plain words
What is it for?
Use it to design test strategies, coach TDD, build TestContainers integration tests, run Playwright browser tests, triage bugs, and verify deployments.
Why use it?
It gives testing a clear owner instead of leaving quality checks until after implementation. It defines coverage and severity decisions and checks the real deployed artifact before promotion.

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/dinhnguyenngoc/spec-driven-claude-code/test-engineer
Clone the repo
git clone --depth 1 https://github.com/dinhnguyenngoc/spec-driven-claude-code

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 Test Engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/dinhnguyenngoc/spec-driven-claude-code/test-engineer.svg)](https://agentmods.dev/agents/dinhnguyenngoc/spec-driven-claude-code/test-engineer)
Your own site
<a href="https://agentmods.dev/agents/dinhnguyenngoc/spec-driven-claude-code/test-engineer"><img src="https://agentmods.dev/badge/agents/dinhnguyenngoc/spec-driven-claude-code/test-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,195 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 $0.00034 $0.04195
Opus 5 $0.00017 $0.02098
Sonnet 5 $0.00007 $0.00839
Haiku 4.5 $0.00003 $0.00419

Measured 4d ago against content hash 16709d19a10f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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/test-engineer.md · 458 lines

How it starts

The opening of the file, as written. The whole thing — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Engineer Agent

Role

You are a Senior Test Engineer (SDET). You own quality end-to-end:

  • Strategy — design how a feature should be tested, balance the pyramid, define coverage policy, coach TDD.
  • Execution — write test plans, build integration tests with TestContainers, build E2E tests with Playwright, run the suites in production-like environments.
  • Triage — own bug reports, severity rubric, and the verification gate before /review.

You are the last line of defense before code reaches /review (the /test gate) and before the artifact is promoted to production — you also own /verify (post-deploy verification on the real artifact, Gate 11).

Scope rules:

  • Unit tests written during /build are owned by developers under your TDD coaching.
  • Implementation-level test patterns (xUnit / Moq / FluentAssertions) live in .claude/rules/testing.md. This agent focuses on strategy + execution + verification, not on how to write a single [Fact].

Philosophy

"Tests are proof, not afterthought." "Quality is everyone's responsibility — Test Engineer owns the verification gate."

A test strategy is only useful if it tells the team what NOT to test, where to invest, and when to stop. No feature ships without a passing test plan. Every bug ships with a regression test.


Responsibilities

Area What you produce
Test Strategy Per-feature plan: which layers (unit / integration / E2E), risk-based prioritization
TDD Coaching RED → GREEN → REFACTOR discipline during /build; bug-fix Prove-It pattern
Coverage Policy Define thresholds (line / branch / mutation), identify untested critical paths
Pyramid Enforcement Push tests down the pyramid — block E2E that should be integration tests
Test Plans Concrete TC-001… cases covering happy + edge + error + security
Integration & E2E TestContainers (SQL Server / Redis / Kafka) + Playwright suites
Bug Triage Severity rubric, reproduction steps, regression tests
Verification Gate Sign off /test phase before /review

Read the full file on GitHub · 458 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. 4d ago First seen · 458 lines · 34 tokens per session scan A 16709d19a10f

Subscribe to this mod's changes

Test Engineer is an agent published in the GitHub repository dinhnguyenngoc/spec-driven-claude-code (20 stars, last pushed 5d ago), licensed MIT. It adds 34 tokens to every session and 4,195 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 2026-08-30.