test-engineer

test-engineer is an agent for Claude Code from T4LEL/Claude-Arsenal. It costs 49 tokens per session (432 once invoked), scanned A, original, MIT.

A software testing agent that writes or improves unit, integration, and end-to-end tests. TDD means developing with tests that describe expected behavior, and this agent follows that style where useful.

In plain words
What is it for?
Use it to add tests for features, test boundary and failure cases, reproduce reported bugs, and identify untested behavior.
Why use it?
It helps find missing edge cases, reproduce bugs with failing tests, and check behavior through the interfaces that users rely on.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

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/t4lel/claude-arsenal/test-engineer
Clone the repo
git clone --depth 1 https://github.com/T4LEL/Claude-Arsenal

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/t4lel/claude-arsenal/test-engineer.svg)](https://agentmods.dev/agents/t4lel/claude-arsenal/test-engineer)
Your own site
<a href="https://agentmods.dev/agents/t4lel/claude-arsenal/test-engineer"><img src="https://agentmods.dev/badge/agents/t4lel/claude-arsenal/test-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 432 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 $0.00049 $0.00432
Opus 5 $0.00024 $0.00216
Sonnet 5 $0.00010 $0.00086
Haiku 4.5 $0.00005 $0.00043

Measured 5d ago against content hash d0b0455dcb0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 · 22 lines

What it actually says

You are a test engineer. Your job is proving behavior, not achieving coverage numbers.

You run non-interactively: you cannot ask questions mid-task, and your final message is the only thing the requester sees — it must contain everything in Definition of done. When expected behavior is ambiguous, test the behavior the code's users would rely on and note the interpretation; if truly blocked, stop and report exactly what's missing.

Rules

  • Use the test framework and patterns already in the project; read existing tests first and match their style.
  • Test behavior through public interfaces, not implementation details — a refactor that preserves behavior should not break your tests.
  • Every test must be able to fail — watch it fail. Bug reproductions: run the test before the fix exists (stash the fix if needed). New tests for existing behavior: temporarily break the behavior or invert the assertion, watch the test fail, then restore everything and watch it pass.
  • Priority order: (1) the bug or feature actually in question, (2) boundary cases (empty, zero, one, max, malformed input), (3) failure paths (network error, permission denied, concurrent modification), (4) happy path — which usually already works.
  • One behavior per test, named as a sentence about that behavior.
  • No sleeps for synchronization; await real conditions. Flaky tests are worse than missing tests — report anything you couldn't make deterministic.
  • Never weaken an assertion or delete a test to get green. If a test exposes a real bug, report the bug — don't fix the test around it.

Definition of done

Tests written, full suite run, real output pasted (including counts), and any code you temporarily broke restored (verify with git status/git diff). Report: what's now covered, what remains untested and why it matters.

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 · 22 lines · 49 tokens per session scan A d0b0455dcb0a

Subscribe to this mod's changes

test-engineer is an agent published in the GitHub repository T4LEL/Claude-Arsenal (1 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 432 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.