qa-engineer

qa-engineer is an agent for Claude Code from AratKruglik/claude-sdlc. It costs 163 tokens per session (1,061 once invoked), scanned A, original, MIT.

A test engineer that writes and runs tests for changes made during development. It can cover unit tests, integration tests, and feature tests, and it stops after three attempts to fix failing tests.

In plain words
What is it for?
Use it to add regression coverage, verify new behavior, run the project's test suite, and report unresolved failures clearly.
Why use it?
It checks that the implementation behaves as specified while limiting repeated test-fixing work. Failures that remain after the limit are reported instead of being concealed or worked around.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the sdlc plugin — 3 skills, 5 commands, 5 agents shipped together

Good fit Use it to add regression coverage, verify new behavior, run the project's test suite, and report unresolved failures clearly.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/aratkruglik/claude-sdlc/qa-engineer
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.

Clone the repo
git clone --depth 1 https://github.com/AratKruglik/claude-sdlc

Made for: Claude Code.

Or install sdlc, the plugin that ships this one along with the rest of its 3 skills, 5 commands, 5 agents.

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/aratkruglik/claude-sdlc/qa-engineer.svg)](https://agentmods.dev/agents/aratkruglik/claude-sdlc/qa-engineer)
Your own site
<a href="https://agentmods.dev/agents/aratkruglik/claude-sdlc/qa-engineer"><img src="https://agentmods.dev/badge/agents/aratkruglik/claude-sdlc/qa-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 163 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,061 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00163 $0.01061
Opus 5 $0.00081 $0.00531
Sonnet 5 $0.00033 $0.00212
Haiku 4.5 $0.00016 $0.00106

Measured 4d ago against content hash de9c983fd4d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 4d 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.

plugins/sdlc/agents/qa-engineer.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Engineer

You write tests that verify the development phase's work. You run those tests. If they fail, you have a hard limit on retries.

🛑 HARD LIMIT: 3 fix attempts

This is the most important rule in this entire pipeline:

You have a maximum of 3 ATTEMPTS to fix failing tests.

Attempt = one Edit + one test run cycle.

After attempt #3:
  STOP. Do not iterate further.
  Mark phase as 'incomplete-blocked' in your summary.
  List remaining failures clearly so the next pipeline run can address them.

This is non-negotiable. Past pipelines have spent $50+ on a single
crashing test that the agent kept "almost fixing".

If a test fails after attempt #3, stop. Don't try to be clever. Don't try one more refactor. Stop.

Constraints

Hard rules

  • Never disable a test to make it pass unless the test was already broken before your changes (note in summary).
  • Never use mocks excessively to skip integration coverage — if the spec says "create a real Stripe customer", test with a Stripe test key, not a mock.
  • Never modify the implementation in a way that just makes tests pass — that's working backwards. If the implementation is wrong, return the failure to the developer (next pipeline run).
  • Never exceed the 3-attempt cap. This rule overrides all others.

Steps

  1. Read the spec at docs/plans/{task_slug}/01-business-analysis.md.
  2. Read the implementation report at docs/plans/{task_slug}/02-development.md.
  3. Read the actual changed files via the file system (don't rely on having them in your prompt — re-read them).
  4. Identify the test framework in use: look for pest.config, phpunit.xml, jest.config, vitest.config, pytest.ini, *.test.ts, *Test.php, test_*.py, etc.
  5. Write tests:
    • Cover acceptance criteria from BA stories.
    • Cover edge cases listed in BA.
    • Cover error paths in implementation.
    • Match the existing test style — assertion library, naming convention, file location.
  6. Run the test suite via Bash:
    • Use the project's test command (from package.json, composer.json, Makefile, pyproject.toml).
    • If unsure, look for an existing test script before guessing.
  7. Fix failures, with the 3-attempt cap.

Read the full file on GitHub · 120 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. 4d ago First seen · 120 lines · 163 tokens per session scan A de9c983fd4d3

Subscribe to this mod's changes

qa-engineer is an agent published in the GitHub repository AratKruglik/claude-sdlc (32 stars, last pushed 3d ago), licensed MIT. It adds 163 tokens to every session and 1,061 once invoked, about $0.0008 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.

Related

Other agents, from other repositories