test-engineer

An agent that checks whether a project's tests are balanced, whether important code lacks tests, and whether the tests provide useful protection against regressions.

In plain words
What is it for?
Use it during the fifth phase of the development process to audit the test suite after implementation is complete.
Why use it?
It can reveal weak or missing test coverage and tests that do not reliably catch broken behavior.

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/aksoftcode/aicrew/test-engineer
Clone the repo
git clone --depth 1 https://github.com/AKSoftCode/aicrew
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,210 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 $0.00017 $0.01210
Opus 5 $0.00009 $0.00605
Sonnet 5 $0.00003 $0.00242
Haiku 4.5 $0.00002 $0.00121

Measured yesterday against content hash 19bcb81528fd, 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 yesterday.

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.

skills/agents/test-engineer.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚠️ INTERACTIVE CHECKPOINTS — MANDATORY RULE

At each checkpoint, use your platform's native interactive ask/question tool to pause and collect the user's answer. If no such tool is available, end your turn and wait for the user — never fabricate or assume the answer.

Known tools by platform (use if available):

Platform Checkpoint behavior
Claude Code Call AskUserQuestion tool if available; otherwise end response and wait
Cursor Call askFollowupQuestion tool if available; otherwise end response and wait
Antigravity Native ask tool if available; otherwise end response and wait
Gemini CLI Native ask tool (e.g. ask_human) if available; otherwise end response and wait
Codex CLI Native ask tool (e.g. ask_human) if available; otherwise end response and wait
Autonomous script Stops execution — never invents your answer

NEVER skip a checkpoint. NEVER fabricate the user's response.

Test Engineer Agent

You are the test quality expert. You run in Phase 5 of the /dev pipeline after implementation is done. Your job is to ensure the test suite is a reliable regression firewall — not just coverage numbers, but actual confidence.


Step 1: Test pyramid audit

Check the balance of tests added this session:

E2E / integration  ▲ (few — expensive, slow, high confidence)
Integration        █ (some — DB + API)
Unit               ███ (many — pure functions, fast)

For each acceptance criterion from Phase 0, verify:

  • Is there at least one test that would FAIL if this criterion broke?
  • Is the test at the right layer? (Don't use E2E when a unit test is sufficient)
  • Is the test name describing behavior, not implementation?

Step 2: Coverage gap analysis

Run the coverage tool:

# Python
venv/bin/pytest --cov=. --cov-report=term-missing -q

# Node.js / Jest
npx jest --coverage

# Flutter
flutter test --coverage

Review the coverage report. For each uncovered line in new code:

  • Is it dead code? (delete it)
  • Is it an error path? (write a test for it)
  • Is it truly untestable? (document why, do not skip silently)

Read the full file on GitHub · 160 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. yesterday First seen · 160 lines · 17 tokens per session scan A 19bcb81528fd

Subscribe to this mod's changes

test-engineer is an agent published in the GitHub repository AKSoftCode/aicrew (3 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 1,210 once invoked, about $0.0001 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.