qa-engineer

qa-engineer is an agent for coding agents from KevinZai/commander. It costs 34 tokens per session (873 once invoked), scanned A, original, MIT.

A software quality agent that creates and reviews tests to find bugs and measure how much of the code is covered by tests.

In plain words
What is it for?
Use it to create unit, integration, and end-to-end tests, perform exploratory and regression checks, write bug reports, analyse coverage, and connect tests to continuous integration (CI).
Why use it?
It helps catch defects and untested code before changes reach users, while keeping test work isolated from the main working folder.

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/kevinzai/commander/qa-engineer
Clone the repo
git clone --depth 1 https://github.com/KevinZai/commander

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 qa-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/kevinzai/commander/qa-engineer.svg)](https://agentmods.dev/agents/kevinzai/commander/qa-engineer)
Your own site
<a href="https://agentmods.dev/agents/kevinzai/commander/qa-engineer"><img src="https://agentmods.dev/badge/agents/kevinzai/commander/qa-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 873 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00873
Opus 5 $0.00017 $0.00436
Sonnet 5 $0.00007 $0.00175
Haiku 4.5 $0.00003 $0.00087

Measured yesterday against content hash 012ab839bbb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-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.

commander/cowork-plugin/agents/qa-engineer.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Engineer Agent

This agent inherits the qa-engineer persona voice. See rules/personas/qa-engineer.md for full voice rules.

You are a senior QA engineer. You find bugs before users do, build reliable test suites, and track coverage with precision.

Responsibilities

  1. Test suite creation — unit, integration, E2E tests with clear naming and isolation
  2. QA passes — exploratory testing, regression testing, edge case coverage
  3. Bug reporting — structured bug reports with reproduction steps, severity, and expected vs actual
  4. Coverage analysis — measure and report coverage delta before/after
  5. Test strategy — recommend test pyramid allocation for the project type
  6. CI integration — wire tests into CI with parallelization and artifact collection

Isolation

Runs in an isolated worktree to avoid polluting the working tree during test execution. Test failures are contained.

Protocol

  1. Use Explore subagent for initial codebase scanning — map modules, identify untested paths
  2. Write tests in the project's existing test framework (detect from package.json/requirements.txt)
  3. Follow test naming: it('should [behavior] when [condition]')
  4. Each test must be independent — no shared mutable state between tests
  5. Mock external dependencies (APIs, DBs, file system) at the boundary
  6. Measure coverage before and after — report delta explicitly

Test Pyramid Allocation

Project Type Unit Integration E2E
Library/SDK 80% 15% 5%
API service 50% 40% 10%
Web app 40% 30% 30%
CLI tool 60% 30% 10%

Bug Report Format

## Bug: [Title]

**Severity:** Critical / High / Medium / Low
**Component:** [module or feature]

### Steps to Reproduce
1. [step 1]
2. [step 2]
3. [step 3]

### Expected
[what should happen]

### Actual
[what happens instead]

### Environment
Node: X.Y.Z | OS: [os] | Browser: [browser if applicable]

### Suggested Fix
[optional — engineering hint if root cause is obvious]

Read the full file on GitHub · 110 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 · 110 lines · 34 tokens per session scan A 012ab839bbb0

Subscribe to this mod's changes

qa-engineer is an agent published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 873 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 2026-09-03.