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 bug-reportgit 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/bug-report)<a href="https://agentmods.dev/skills/akovalion/paranoid-qa/bug-report"><img src="https://agentmods.dev/badge/skills/akovalion/paranoid-qa/bug-report.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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.
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 | $0.00041 | $0.01219 |
| Opus 5 | $0.00020 | $0.00609 |
| Sonnet 5 | $0.00008 | $0.00244 |
| Haiku 4.5 | $0.00004 | $0.00122 |
Grade A, and why
bug-report 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 8d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ты помогаешь быстро завести баг в Jira. Работай по этому алгоритму:
0. Конфигурация проекта (заполните под свой Jira)
Значения ниже — пример; адаптируйте под свой инстанс (прямо здесь или в CLAUDE.md проекта):
- Проект по умолчанию:
PROJ - Тип задачи для дефекта:
Bug(проверьте точное имя типа в своём проекте — в русскоязычных инстансах часто «Дефект») - Значения приоритета: как в вашем Jira (напр. Highest / High / Medium / Low — или локализованные)
- Обязательные кастомные поля: во многих проектах создание тикета падает без них. Пример формата:
customfield_XXXXX(Team):"..."customfield_XXXXX(Среда обнаружения):{"value": "Test"}; для бага, найденного на проде —{"value": "Prod"}Свои поля и допустимые значения найдите черезjira_search_fieldsиjira_get_field_options, либо посмотрите заполненные поля свежего дефекта коллег черезjira_get_issue. Две частые ловушки. Первая: форма записи не совпадает с формой чтения - часть полей принимает только строку и отвечает ошибкой «не найдено значение» на объект{"value": ...}, хотя при чтении того же поля возвращается именно объект; не копируйте прочитанное обратно в запись вслепую. Вторая: уровень безопасности (security) в закрытых проектах обязателен, но в сообщении об ошибке называется не всегда. Собрав рабочий набор один раз, зафиксируйте его в локальном скилле или памяти проекта - иначе каждое заведение дефекта начинается с доисследования.
1. Сбор данных
Если пользователь передал описание бага в аргументах - используй его. Если нет - задай вопросы через AskUserQuestion:
Обязательные данные:
- Что произошло (фактический результат)
- Что ожидалось (ожидаемый результат)
- Шаги воспроизведения
- Окружение (стенд, браузер, устройство)
Опциональные:
- Проект (по умолчанию — из конфигурации)
- Приоритет (по умолчанию средний)
- Assignee
2. Формат тикета
Тип и приоритет — по конфигурации (раздел 0).
Заголовок (summary): краткое описание проблемы, без префиксов [BUG] и т.п.
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.
- 8d ago First seen · 106 lines · 41 tokens per session scan A bcebad99d7b5
bug-report is a skill published in the GitHub repository akovalion/paranoid-qa (13 stars, last pushed 6d ago), licensed MIT. It adds 41 tokens to every session and 1,219 once invoked, about $0.0002 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
test-plan
Build a test plan when a new Epic is created. Pulls epic details and linked stories from Jira, analyzes scope, and produces a test plan covering strategy, automation gap analysis, success criteria, environment needs, and risks. Output goes to Confluence and local test knowledge base. Use when: "test plan", "plan tests…
review-ticket
Review a Jira ticket during backlog grooming or refinement. Audits the ticket for testability, AC completeness, missing edge cases, and potential blockers. Outputs a structured review the SDT can bring to the grooming session. Use when: "review this ticket", "check ACs", "testability review", "grooming". Do NOT use…
setup
First-run configuration wizard for QABuddy. Sets up context source (Jira, spec docs, chat, custom), team mode (solo vs PR-based), and project preferences. Writes .qabuddy.json to the project root. Re-run to reconfigure. Use when: "setup", "configure", "first time setup", "change settings". Do NOT use when: asking…
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…
syndic
Gère un parc de copropriétés en France avec vue portfolio consolidée. Couvre administration, comptabilité (décret 2005, plan comptable copro, 5 annexes), assemblées générales (convocation, PV, notification), appels de fonds, travaux, fournisseurs, recouvrement d'impayés et transition de syndic. Maîtrise les majorités…
contact-cache
Track all identified/contacted people across strategies. CSV-backed contact database with dedup by LinkedIn URL or email. Prevents duplicate outreach when running strategies on a recurring cadence.