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.
npx skills add akovalion/paranoid-qa --skill test-reviewgit clone --depth 1 https://github.com/akovalion/paranoid-qaWrote 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/skills/akovalion/paranoid-qa/test-review)<a href="https://agentmods.dev/skills/akovalion/paranoid-qa/test-review"><img src="https://agentmods.dev/badge/skills/akovalion/paranoid-qa/test-review/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/skills/akovalion/paranoid-qa/test-review"><img src="https://agentmods.dev/badge/skills/akovalion/paranoid-qa/test-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- medium MCP Rug Pull · line 47 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00119 | $0.06120 |
| Opus 5 | $0.00060 | $0.03060 |
| Sonnet 5 | $0.00024 | $0.01224 |
| Haiku 4.5 | $0.00012 | $0.00612 |
Grade A, and why
test-review 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 10d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ревью автотестов (TypeScript + Playwright)
Проверь только что написанный или изменённый тест-код на соответствие best practices и выдай приоритизированный список замечаний с фиксами. Источник правил — официальная документация Playwright (best-practices, locators, test-assertions) и TypeScript + конвенции конкретного проекта.
Источник правды по проекту — его корневой
CLAUDE.md(если есть) и стиль соседнего кода. Этот скилл — фаза проверки: он дополняет проектные правила, не заменяет их. Развёрнутые❌ до → ✅ послеи ссылки на источники по каждому правилу — вreferences/rules-catalog.md.
Когда применять и режим работы
- Режим по умолчанию — диагностика. Прочитать код, прогнать статический анализ, выдать отчёт. Файлы не править, пока пользователь явно не попросит «применяй / чини». Тогда — итеративно, по одному изменению с прогоном между ними (не big-bang переписывание рабочего теста).
- Scope — только новое/изменённое, не весь suite. По умолчанию — незакоммиченные изменения (
git status+git diff). Если пользователь указал файл/папку — ревьюй их. - Любой тип теста: UI E2E, API, UI+API, visual regression, mobile, моки, а также Page Object, фикстуры, константы.
- Не уходи в автономные действия за пределами ревью (воспроизведение через браузер, прогон всего suite, правки) без подтверждения — задача по умолчанию «прочитать и оценить».
Доказательная дисциплина (без галлюцинаций)
- Каждое замечание — по реально прочитанной строке (
file:line) или по наблюдённому выводу typecheck / lint / прогона. Не выдумывай нарушения «по аналогии» и не ссылайся на строки, которых не видел. - Правило проверяется инструментом (tsc, ESLint, прогон) → сначала запусти инструмент, потом репорти его вывод, а не «вероятно есть».
- Не уверен, что это дефект, а не осознанное решение проекта → помечай «под вопросом», не утверждай. Сверяйся с
CLAUDE.mdпроекта и соседним кодом: часть «анти-паттернов» может быть намеренной (легаси-хелперы, нестандартная разметка, осознанные исключения из правил). Имена файлов/эндпоинтов/селекторов из памяти и прошлого контекста — фон, перепроверяй на живом коде. - Не нашёл нарушений в категории — так и пиши «чисто», не придумывай замечание ради объёма.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 184 lines · 119 tokens per session scan A 8de97a5cf7e1
test-review is a skill published in the GitHub repository akovalion/paranoid-qa (13 stars, last pushed 9d ago), licensed MIT. It adds 119 tokens to every session and 6,120 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
mk:qa
Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a…
daa-review
Use when reviewing existing test code for DAA compliance, identifying anti-patterns, or suggesting improvements to automation test architecture.
qa-expert
Expert-level quality assurance, testing strategies, automation, and QA processes. Use when the user mentions testing, test automation, quality assurance, or Selenium, or when the task involves Testing Types, QA Processes, Test Strategy, or Defect Management.
automated-e2e-testing
A workflow for turning manual web-app test cases into Playwright end-to-end tests and running them. End-to-end tests check a complete user flow through the website.
qawolf-cli
Manage QA Wolf through the qawolf CLI. Use when asked to create, update, or list coverage requests, bug reports, or maintenance reports; start a run of flows or tags on the QA Wolf platform or read a run's results; list, set, or delete environment variables; manage environments, flows, or tags; request automation of…
e2e-reviewer
Use when reviewing Playwright or Cypress E2E specs, Page Objects (POM), PRs, pull requests, patches, diffs, or changed test files — asked to review tests, audit test quality, or find weak, flaky, or silently-passing tests; when tests pass CI but prove nothing or miss bugs; when auditing missing awaits, vacuous or…