Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Desko77/cursor-1c-skillsnpx agentmods add skills/desko77/cursor-1c-skills/1c-meta-validateWrote 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/1c-meta-validate)<a href="https://agentmods.dev/skills/desko77/cursor-1c-skills/1c-meta-validate"><img src="https://agentmods.dev/badge/skills/desko77/cursor-1c-skills/1c-meta-validate/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/1c-meta-validate"><img src="https://agentmods.dev/badge/skills/desko77/cursor-1c-skills/1c-meta-validate.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00035 | $0.00802 |
| Opus 5 | $0.00017 | $0.00401 |
| Sonnet 5 | $0.00007 | $0.00160 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
1c-meta-validate 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 9d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/meta-validate - валидация объекта метаданных 1С
Проверяет XML объекта метаданных из выгрузки конфигурации на структурные ошибки.
Параметры
| Параметр | Обяз. | Умолч. | Описание |
|---|---|---|---|
| ObjectPath | да | - | Путь к XML-файлу или каталогу. Через | для batch |
| Detailed | нет | - | Подробный вывод (все проверки, включая успешные) |
| MaxErrors | нет | 30 | Остановиться после N ошибок (per object) |
| OutFile | нет | - | Записать результат в файл (UTF-8 BOM) |
| IndexPath | нет | - | Индекс конфигурации от 1c-config-index: включает сверку ссылочных типов с остальной конфигурацией |
Команда
powershell.exe -NoProfile -File skills/1c-meta-validate/scripts/meta-validate.ps1 -ObjectPath "Catalogs/Номенклатура/Номенклатура.xml"
powershell.exe -NoProfile -File skills/1c-meta-validate/scripts/meta-validate.ps1 -ObjectPath "Catalogs/Банки|Documents/Заказ"
Сверка ссылочных типов (проверка 16)
Реквизит с типом CatalogRef.Контрагенты при отсутствующем справочнике проходил валидацию: объект
проверялся сам по себе. Проверка 16 закрывает это - она сверяет типы реквизитов, измерений,
ресурсов, реквизитов табличных частей и значение самого объекта с тем, что есть в конфигурации.
Два источника ответа:
-IndexPath- индекс от навыка1c-config-index. Точный ответ: индекс несет ВСЕ порождаемые типы конфигурации, включаяCharacteristic.ВидыСубконтоиDefinedType.МойТип. Строится один раз на прогон, поэтому годится для проверки всей конфигурации подряд.- Без него - резерв: объект ищется файлом в каталоге конфигурации. Для одного объекта дешево, на всей конфигурации - обход каталога на каждую ссылку.
Нет ни того, ни другого (одиночный файл вне выгрузки) - проверка не выполняется и прямо об этом сообщает. Молчать нельзя: молчание читалось бы как "нарушений нет".
Тяжесть всегда предупреждение, не ошибка. Проверяется ОДИН объект, и валидатор не знает, полна ли
выгрузка: файл могли достать из конфигурации побольше. В расширении и у заимствованного объекта
(ObjectBelonging = Adopted) формулировка мягче - там ссылка на основную конфигурацию нормальна.
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.
- 9d ago First seen · 56 lines · 35 tokens per session scan A 50b6e191831a
1c-meta-validate is a skill published in the GitHub repository Desko77/cursor-1c-skills (57 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 802 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 2026-09-03.
Other skills, from other repositories
1c-web-test
A browser-automation tool for testing the 1C:Enterprise web client. It uses scripted actions to navigate screens, fill forms, read tables and reports, and apply filters.
1c-vanessa-steps
A searchable catalogue of 1,569 Vanessa Automation steps, with tools for finding steps and checking Gherkin scenarios. Gherkin is the plain-language format used by behavior-driven tests, where each sentence maps to an implemented test action.
1c-epf-validate
A validator for 1C external reports and external processing files. It checks their XML structure and the objects, properties, forms, and layouts they contain.
1c-cf-validate
A validator for 1C configuration files, where 1C is business software commonly used for accounting and enterprise operations.
1c-interface-validate
A validator for the command interface of a 1C subsystem. This interface is the menu and command structure users see for that part of a 1C application.
composing-1c-queries
A guide for writing queries in the 1C:Enterprise query language. It covers how to select, filter, join, group, and summarize data from 1C catalogs, documents, and registers.