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.
/plugin marketplace add akovalion/paranoid-qanpx agentmods add plugins/akovalion/paranoid-qa/rugit clone --depth 1 https://github.com/akovalion/paranoid-qaGrade A, and why
paranoid-qa-ru 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 2d 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.
What it actually says
{
"name": "paranoid-qa-ru",
"description": "Русская версия paranoid-qa: дотошный QA-агент с доказательной дисциплиной - каждый вердикт только по наблюдённому артефакту. Фреймворк тестирования, ревью Playwright-тестов, тест-кейсы, баг-репорты в Jira.",
"version": "1.0.0",
"author": {
"name": "Aleksei Kovalev"
},
"homepage": "https://github.com/akovalion/paranoid-qa",
"license": "MIT",
"keywords": ["qa", "testing", "playwright", "test-review", "evidence"]
}
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.
- 2d ago First seen · 12 lines scan A c2a2b4ec07d5
paranoid-qa-ru is a plugin published in the GitHub repository akovalion/paranoid-qa (13 stars, last pushed 7d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
qa-skills
Deterministic, evidence-backed QA runtime for Claude Code, Codex, and Cursor. Versioned artifact contracts, a Playwright Runtime Browser Driver, redacted evidence, and reproducible release gates. The runtime never calls an LLM.
qa-skills-bootstrap
Bootstraps @gwinnguyen/qa-skills in a project: resolves the local runtime, verifies its version range, installs the checksummed canonical Skill Bundle, and verifies the Runtime Binding. The eight QA skills themselves are installed by the runtime, never copied by this plugin.
sniff
Autonomous QA scanner via sniff-qa: walks your running app in a real browser and reports real bugs (broken pages/links, console/network errors, broken forms, state-loss, empty/placeholder data, bad loading/error states, responsive + a11y) with reproduction proof, severity, confidence, and a fix. No API key.
playwright-rust
Procedural reference for writing Rust browser automation with playwright-rs: adding the crate and installing its browsers, object model, the locator!() macro, builder options, auto-wait semantics, and trace capture.
paad
Architecture analysis, code quality, and development workflow skills by Ovid.
junior-flow
Helps junior developers create technical story markdown from a story tracker.