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 Desko77/cursor-1c-skills --skill report-issuegit clone --depth 1 https://github.com/Desko77/cursor-1c-skillsWrote 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/desko77/cursor-1c-skills/report-issue)<a href="https://agentmods.dev/skills/desko77/cursor-1c-skills/report-issue"><img src="https://agentmods.dev/badge/skills/desko77/cursor-1c-skills/report-issue/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/desko77/cursor-1c-skills/report-issue"><img src="https://agentmods.dev/badge/skills/desko77/cursor-1c-skills/report-issue.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 | $0.00093 | $0.01341 |
| Opus 5.5 | $0.00037 | $0.00536 |
| Sonnet 5.5 | $0.00019 | $0.00268 |
| Haiku 4.5 | $0.00009 | $0.00134 |
Grade A, and why
report-issue 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 25d 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.
This is a copy
97% identical to report-issue — 76 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/report-issue - дефект или пожелание разработчикам набора
Готовит issue в репозиторий набора или плагина AI-EDT: проверяет, что дефект наш, ищет дубликат, собирает обезличенный черновик, проверяет его скриптом на приватные данные и отправляет только после согласия пользователя.
Когда НЕ применять
- Ошибка в конфигурации, данных или настройках пользователя, а не в скиле, правиле или плагине - объяснить пользователю, issue не заводить.
- Сбой среды: нет платформы, не запущена EDT, нет прав, нет сети.
- Чужой продукт: платформа 1С, другой плагин EDT, Claude Code, Cursor - назвать, куда сообщить, самому не отправлять.
- Вопрос или обсуждение без дефекта - Telegram: Скилы и правила, Плагин.
Куда
| Что | Репозиторий |
|---|---|
| Скрипт скила или правило, агент в Claude Code | Desko77/claude-code-skills-1c |
| Скрипт скила или правило, агент в Cursor | Desko77/cursor-1c-skills |
Инструмент MCP-сервера AI-EDT (ключ ai-edt) |
Desko77/ai-edt |
Метки: дефект - bug, пожелание - enhancement; всегда from-agent.
Шаги
- Убедиться, что дефект наш. Назвать скил, правило или инструмент и воспроизведение: команда, вход, фактический результат, ожидаемый результат. Готово, когда воспроизведение есть, а не догадка о причине.
- Найти дубликат. При установленном
gh:gh issue list --repo <репозиторий> --state all --search "<ключевые слова>". Безgh- дать пользователю ссылкуhttps://github.com/<репозиторий>/issues?q=<ключевые слова>. Нашлась такая же issue - предложить дописать в нее комментарий вместо новой. Готово, когда поиск выполнен и результат назван. - Черновик. Текст записать во временный файл вне репозитория пользователя (каталог временных
файлов). Заголовок:
<скил или инструмент>: <что не так>, до 80 символов.
- Дефект - разделы "Что произошло", "Как воспроизвести", "Ожидалось", "Среда" (версия набора или плагина, Claude Code или Cursor, PowerShell или Python, версия платформы 1С, ОС).
- Пожелание - разделы "Задача", "Чего не хватает", "Как могло бы работать".
- Обезличивание: объекты -
Catalog.Товары,Document.Продажа; путь -C:/Projects/my-project; база -my-base. Текст ошибки платформы и код выхода сохраняются дословно. Фрагмент кода - минимальный, на обобщенных именах. Выгрузки, логи целиком и скриншоты с данными не прикладываются.
What ships with it
2 files 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.
- 25d ago First seen · 77 lines · 93 tokens per session scan A bf4296855856
report-issue is a skill published in the GitHub repository Desko77/cursor-1c-skills (70 stars, last pushed 16d ago), licensed MIT. It adds 93 tokens to every session and 1,341 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to report-issue, differing in 76 lines, and is treated as a copy.
Other skills, from other repositories
1c-bsl-validate
A checker for calls to shared 1C modules, using an exported configuration index. Shared modules are reusable code units that other parts of a 1C application can call.
1c-query-validate
A checker for 1C database queries. It compares the tables, records, virtual tables, and fields named in a query with an index of the 1C configuration.
1c-meta-validate
A checker for XML metadata objects in a 1C configuration. Metadata describes parts of a 1C application, such as catalogues, documents, registers, and their fields.
1c-subsystem-validate
A validator for the XML file that defines a 1C subsystem. It checks the structure and can compare the subsystem's contents with objects in the full configuration.
1c-xdto-validate
A checker for 1C XDTO packages and their connection to a configuration. It reports errors that could make 1C reject the package or interpret its data incorrectly at runtime.
1c-cfe-validate
A validator for 1C configuration extensions, called CFE files. It checks the extension’s XML, properties, contents, borrowed objects, and—when given the main configuration—form data paths.