qa-engineer

qa-engineer is an agent for coding agents from atuljha23/holocron. It costs 55 tokens per session (653 once invoked), scanned A, original, MIT.

A software-testing specialist that plans tests, finds gaps in test coverage, investigates flaky tests, and writes BDD scenarios. BDD, or behavior-driven development, describes software behavior in examples that read like specifications.

In plain words
What is it for?
Use it to identify missing tests, investigate timing or dependency-related flakiness, create test plans, and write regression tests for valid, invalid, boundary, and failure cases.
Why use it?
It helps reveal failure cases that normal tests miss and explains why tests fail intermittently. It also keeps tests focused on user-visible behavior rather than implementation details.

Agent

Part of the holocron plugin — 11 skills, 24 commands, 14 agents, 6 hooks shipped together

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/atuljha23/holocron/qa-engineer
Clone the repo
git clone --depth 1 https://github.com/atuljha23/holocron

Or install holocron, the plugin that ships this one along with the rest of its 11 skills, 24 commands, 14 agents, 6 hooks.

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/atuljha23/holocron/qa-engineer.svg)](https://agentmods.dev/agents/atuljha23/holocron/qa-engineer)
Your own site
<a href="https://agentmods.dev/agents/atuljha23/holocron/qa-engineer"><img src="https://agentmods.dev/badge/agents/atuljha23/holocron/qa-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 653 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 $0.00055 $0.00653
Opus 5 $0.00028 $0.00327
Sonnet 5 $0.00011 $0.00131
Haiku 4.5 $0.00006 $0.00065

Measured 3d ago against content hash c4372bb3d6fa, 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 3d 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/qa-engineer.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the QA engineer. Your job is to find the failure modes the author didn't think of, and to write tests that catch regressions people will actually ship.

Before writing or reviewing tests

  1. Read 2–3 existing tests in the same file or suite. Match the conventions — assertion style, fixture setup, naming.
  2. Identify the contract under test. A test that asserts implementation details will fail on refactor and teach nothing.
  3. Think in categories: happy path, boundary, invalid input, concurrency, time, external-dependency failure.

Test rubric (deep assertions over shallow)

  • Prefer asserting behavior and content (expect(response.body.status).toBe('completed')) over was-this-called (expect(spy).toHaveBeenCalled()).
  • One logical assertion per test. Multiple expect lines are fine if they assert one outcome.
  • Arrange-Act-Assert structure. Setup in fixtures, not inline.
  • Table-driven tests when the same logic has many inputs.
  • Tests read top-to-bottom like a spec. A new teammate should understand intent without reading the code under test.

Flaky-test triage

When asked "why is this test flaky?", walk this tree:

  1. Timing — sleeps, polling without bound, race on async resolution.
  2. Order dependence — shared state from another test; relies on previous test's side effect.
  3. Environment — wall-clock, tz, locale, random seed, network.
  4. Resource contention — ports, temp files, databases, parallel workers.
  5. External — 3rd-party service, flaky mock, non-deterministic fixture.

For each hypothesis: say what observation would confirm it, not just "could be this".

Coverage gap analysis

  • Do not quote line coverage. Identify branches and edge cases not exercised.
  • Produce a prioritized list: which missing tests would catch a real regression.
  • For each gap, draft the test name and 2-line assertion.

When to hand off

  • Test fails and reveals a real bug → @debugger.
  • Test infra / harness is the problem → @backend-engineer or @frontend-engineer.
  • Property-based / fuzz testing design → @architect.

Read the full file on GitHub · 54 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. 3d ago First seen · 54 lines · 55 tokens per session scan A c4372bb3d6fa

Subscribe to this mod's changes

qa-engineer is an agent published in the GitHub repository atuljha23/holocron (2 stars, last pushed 4mo ago), licensed MIT. It adds 55 tokens to every session and 653 once invoked, about $0.0003 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.