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/claude-code-skills-1cnpx agentmods add skills/desko77/claude-code-skills-1c/1c-query-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/claude-code-skills-1c/1c-query-validate)<a href="https://agentmods.dev/skills/desko77/claude-code-skills-1c/1c-query-validate"><img src="https://agentmods.dev/badge/skills/desko77/claude-code-skills-1c/1c-query-validate.svg" alt="Measured on agentmods" 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 | $0.00060 | $0.01434 |
| Opus 5 | $0.00030 | $0.00717 |
| Sonnet 5 | $0.00012 | $0.00287 |
| Haiku 4.5 | $0.00006 | $0.00143 |
Grade A, and why
1c-query-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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- 1c-query-validate — 86% identical, 29 lines differ
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/query-validate - проверка запроса по выгрузке
Берет текст запроса и индекс конфигурации, отвечает на один вопрос: все ли имена в запросе существуют. Опечатка в имени таблицы или поля ловится до того, как запрос попадет в базу.
Работает без EDT, без платформы и без базы.
Параметры
| Параметр | Обяз. | Умолч. | Описание |
|---|---|---|---|
| QueryPath | * | - | Файл с текстом запроса |
| Query | * | - | Текст запроса прямо в аргументе |
| IndexPath | да | - | Индекс от 1c-config-index |
| Detailed | нет | - | Показать счетчики проверенного даже когда есть замечания |
| MaxErrors | нет | 30 | Не выводить больше N замечаний |
* Нужен ровно один из QueryPath и Query.
Команда
python skills/1c-config-index/scripts/config-index.py -ConfigPath src -OutFile .cache/index.json
python skills/1c-query-validate/scripts/query-validate.py -QueryPath запрос.txt -IndexPath .cache/index.json
powershell.exe -NoProfile -File "skills/1c-query-validate/scripts/query-validate.ps1" -QueryPath "запрос.txt" -IndexPath ".cache/index.json"
Что проверяется
Имена метаданных где угодно в тексте. Двухчастное имя вида Справочник.Контрагенты проверяется
на существование объекта - в ИЗ, в ВЫРАЗИТЬ ... КАК, в ССЫЛКА, в ЗНАЧЕНИЕ, в условиях. Оба
языка запроса: Catalog.Контрагенты разбирается так же.
Третья часть - только в позиции таблицы (после ИЗ, FROM, СОЕДИНЕНИЕ, JOIN):
- у объектов - табличная часть:
Документ.Накладная.Товары; - у регистров - виртуальная таблица:
РегистрНакопления.Остатки.ОстаткиИОбороты. Список закрытый, незнакомое имя дает замечание.
Вне позиции таблицы третья часть не трогается: там она может быть значением перечисления
(ЗНАЧЕНИЕ(Перечисление.Статусы.Новый)), пустой ссылкой или предопределенным элементом.
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.
- 4d ago First seen · 99 lines · 60 tokens per session scan A e17068625a50
1c-query-validate is a skill published in the GitHub repository Desko77/claude-code-skills-1c (56 stars, last pushed 6d ago), licensed MIT. It adds 60 tokens to every session and 1,434 once invoked, about $0.0003 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-query-validate
A checker for 1C query text against an exported configuration index. It verifies that referenced tables, register tables, tabular parts, and fields exist.
1c-skd-validate
A checker for a 1C data composition schema, the XML definition that describes how a report builds and presents data. It checks structure, references, duplicate names, and optionally whether referenced objects exist in the configuration.
1c-subsystem-validate
A checker for the XML definition of a 1C subsystem. It verifies the subsystem's structure and can compare its listed contents with objects that actually exist in the configuration.
1c-cfe-validate
A validator for a CFE, the extension format used to modify a 1C configuration, that checks its XML structure and included objects.
1c-db-load-cf
A tool that imports a CF file into a 1C information base. A CF file is a binary package containing a 1C configuration.
1c-db-dump-cf
A tool that exports the configuration of a 1C information base to a CF file. A CF file contains the configuration, but not the database's business data.