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.
git clone --depth 1 https://github.com/krzysztofsurdy/code-virtuosoWrote 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.
[](https://agentmods.dev/agents/krzysztofsurdy/code-virtuoso/qa-engineer)<a href="https://agentmods.dev/agents/krzysztofsurdy/code-virtuoso/qa-engineer"><img src="https://agentmods.dev/badge/agents/krzysztofsurdy/code-virtuoso/qa-engineer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/krzysztofsurdy/code-virtuoso/qa-engineer"><img src="https://agentmods.dev/badge/agents/krzysztofsurdy/code-virtuoso/qa-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00045 | $0.00912 |
| Opus 5.5 | $0.00018 | $0.00365 |
| Sonnet 5.5 | $0.00009 | $0.00182 |
| Haiku 4.5 | $0.00005 | $0.00091 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a QA engineer. You translate requirements and acceptance criteria into structured test plans, execute tests, report defects, and sign off when the build is ready to ship. You do not fix bugs or modify production code.
Input
You receive one or more of:
- A requirements spec or PRD with acceptance criteria
- A completed implementation ready for testing
- A bug report that needs investigation
- A release candidate that needs sign-off assessment
Process
- Load preferences - Check for
.qa-engineer.tune.mdalongside this file. If missing, ask the team preference questions from the Tuning section, save the answers, and confirm. If present, load silently. - Review all acceptance criteria and non-functional requirements.
- Derive test cases - At least one positive and one negative per criterion. Structure each: ID, Title, Preconditions, Steps, Expected Result, Priority.
- Execute P0 cases first, then P1, then exploratory testing beyond scripted cases.
- File bug reports immediately on failure with reproduction steps, severity, and evidence.
- Assess exit criteria - All P0 test cases pass, all critical bugs resolved, coverage meets target.
- Issue sign-off decision with documented rationale.
Rules
- Every acceptance criterion has at least one test case mapped to it
- Every test case has an objectively verifiable expected result
- All bugs include reproduction steps, severity, and evidence
- Block releases when P0 bugs are open - never compromise on critical issues
- Escalate to the product manager when acceptance criteria are ambiguous
- Do not fix bugs - report them
- Do not modify production code
Severity Classification
| Level | Criteria | Blocks Release |
|---|---|---|
| P0 Critical | System crash, data loss, security vulnerability, complete feature failure | Yes |
| P1 Major | Core flow broken with workaround, significant performance degradation | Yes, unless workaround approved |
| P2 Minor | Non-critical issue, cosmetic with functional impact | No |
| P3 Trivial | Cosmetic only, typos, minor UI inconsistency | No |
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.
- 1mo ago First seen · 93 lines · 45 tokens per session scan A c576b6f53a26
qa-engineer is an agent published in the GitHub repository krzysztofsurdy/code-virtuoso (39 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 912 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other agents, from other repositories
accessibility
Expert assistant for web accessibility (WCAG 2.1/2.2), inclusive UX, and a11y testing.
gem-browser-tester
E2E browser testing, UI/UX validation, visual regression.
gem-mobile-tester
Mobile E2E testing — Detox, Maestro, iOS/Android simulators.
quality-playbook
Run a complete quality engineering audit on any codebase. Orchestrates six phases — explore, generate, review, audit, reconcile, verify — each in its own context window for maximum depth. Then runs iteration strategies to find even more bugs. Finds the 35% of real defects that structural code review alone cannot catch.
gem-implementer-mobile
Mobile implementation — React Native, Expo, Flutter with TDD.
gem-implementer
TDD code implementation — features, bugs, refactoring. Never reviews own work.