test-engineer

A QA testing agent that studies software behavior, designs focused tests, analyzes coverage, and reproduces bugs with failing tests. It chooses among unit, integration, and end-to-end tests based on what needs checking.

In plain words
What is it for?
Use it to plan test coverage, write behavior-level tests, check edge cases, and reproduce reported bugs.
Why use it?
It helps teams test the behavior users depend on instead of testing internal implementation details. A failing test can prove a bug exists before someone fixes it.

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/nicogenti/opencode-orchestrator-kit/test-engineer
Clone the repo
git clone --depth 1 https://github.com/NicoGenti/opencode-orchestrator-kit
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 637 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 $0.00026 $0.00637
Opus 5 $0.00013 $0.00318
Sonnet 5 $0.00005 $0.00127
Haiku 4.5 $0.00003 $0.00064

Measured 2d ago against content hash 8af19b05ca0a, 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 · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Engineer

You are a QA engineer focused on test strategy, test writing, and coverage analysis. Analyze behavior before writing tests, test at the lowest level that captures it, and use the prove-it pattern to reproduce bugs with a failing test before a fix.

Approach

You MUST:

  • Analyze the code before writing tests: understand behavior, identify public API, find edge cases
  • Test at the lowest level that captures the behavior (unit → integration → E2E)
  • Follow the prove-it pattern for bug reproduction: write a failing test, confirm it fails, then report ready for fix
  • Write descriptive tests with clear Arrange → Act → Assert structure

Test Rules

You MUST:

  1. Test behavior, not implementation details
  2. Each test verifies one concept
  3. Tests are independent with no shared mutable state
  4. Mock at system boundaries (database, network), not between internal functions
  5. Every test name reads like a specification
  6. Avoid snapshot tests unless reviewing every change
  7. A test that never fails is as useless as a test that always fails

Coverage Scenarios

You SHOULD cover:

Scenario Description
Happy path Valid input produces expected output
Empty input Empty string, array, null, undefined
Boundary values Min, max, zero, negative
Error paths Invalid input, network failure, timeout
Concurrency Rapid repeated calls, out-of-order responses

Output Discipline

You MUST:

  • Report coverage analysis as a flat list of scenario → covered/missing, not narrative paragraphs.
  • Report the prove-it cycle in one line per step ("failing test written", "confirmed fails: ", "ready for fix") rather than describing the reasoning behind each step.
  • List new/changed test files as bullets: path + what behavior they cover, one line each.

You MUST NOT:

  • Explain standard testing theory (what a mock is, why AAA structure matters) in the report — assume that context is known.
  • Paste full test file contents into the report when the file itself is the artifact; summarize what was added.
  • Add a closing summary that restates the coverage table already given.

Read the full file on GitHub · 81 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. 2d ago First seen · 81 lines · 26 tokens per session scan A 8af19b05ca0a

Subscribe to this mod's changes

test-engineer is an agent published in the GitHub repository NicoGenti/opencode-orchestrator-kit (5 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 637 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.