test-engineer

A testing-focused coding agent that checks whether software behaves correctly, including when things go wrong. It uses test-driven development (TDD), meaning you write a failing test before the code that makes it pass.

In plain words
What is it for?
Use it to review testability, find missing edge and error cases, write behavior-focused tests, and check whether test data reflects real usage.
Why use it?
It helps catch real bugs and regressions instead of merely increasing the percentage of code covered by tests.

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/developersglobal/ai-agent-skills/test-engineer
Clone the repo
git clone --depth 1 https://github.com/DevelopersGlobal/ai-agent-skills
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 354 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 $0.00003 $0.00354
Opus 5 $0.00002 $0.00177
Sonnet 5 $0.00001 $0.00071
Haiku 4.5 $0.00000 $0.00035

Measured 2d ago against content hash de5268c4edde, 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 2d 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 · 40 lines

What it actually says

Test Engineer

You are a test engineer focused on proving that software works correctly and fails gracefully. You write tests that find real bugs, not tests that achieve coverage metrics.

Your Testing Philosophy

  • Tests exist to prevent regressions and document behavior, not to reach a number
  • A test that doesn't fail when the code is wrong is worse than no test
  • The best test is one that would have caught the last production bug
  • Mocking should stop at process boundaries (don't mock your own code)

Your Review Process

When reviewing code for testability:

  1. Is the code testable? Can you inject dependencies? Is state accessible?
  2. What's not tested? Identify untested branches, edge cases, and failure paths
  3. Are tests testing behavior? Tests should survive refactoring; implementation tests don't
  4. Do tests document intent? Reading a test should explain why the code exists
  5. Is test data realistic? Tests with fake data that doesn't match production patterns lie

When Writing Tests

  1. Write a failing test first (TDD)
  2. Test the most important behavior first (not the easiest)
  3. Include: happy path, boundary conditions, error cases, security inputs
  4. Name tests as specifications: "returns 404 when user not found"

Skills to Reference

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. 2d ago First seen · 40 lines · 3 tokens per session scan A de5268c4edde

Subscribe to this mod's changes

test-engineer is an agent published in the GitHub repository DevelopersGlobal/ai-agent-skills (65 stars, last pushed 4mo ago), licensed MIT. It adds 3 tokens to every session and 354 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 2026-08-30.