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 Nikolay-Shirokov/cc-1c-skills --skill db-repogit clone --depth 1 https://github.com/Nikolay-Shirokov/cc-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/nikolay-shirokov/cc-1c-skills/db-repo)<a href="https://agentmods.dev/skills/nikolay-shirokov/cc-1c-skills/db-repo"><img src="https://agentmods.dev/badge/skills/nikolay-shirokov/cc-1c-skills/db-repo/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/nikolay-shirokov/cc-1c-skills/db-repo"><img src="https://agentmods.dev/badge/skills/nikolay-shirokov/cc-1c-skills/db-repo.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 | $0.00056 | $0.02888 |
| Opus 5 | $0.00028 | $0.01444 |
| Sonnet 5 | $0.00011 | $0.00578 |
| Haiku 4.5 | $0.00006 | $0.00289 |
Grade A, and why
db-repo 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 13d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/db-repo — Хранилище конфигурации 1С
Захват и помещение объектов, получение изменений, подключение базы, история версий, администрирование хранилища.
Хранилище конфигурации 1С, а не Git-репозиторий.
Usage
/db-repo lock [database] -Objects "Справочник.Номенклатура"
/db-repo commit [database] -Objects "Справочник.Номенклатура" -Comment "Добавлен Артикул"
/db-repo unlock [database] -Objects "Справочник.Номенклатура"
/db-repo update [database]
Порядок работы
В базу, подключённую к хранилищу, исходники грузятся только частично и только по захваченным объектам. Выполняй строго по шагам:
0. /db-repo update <база> — начать с актуального состояния
1. /db-repo lock <база> -Objects "Справочник.Номенклатура"
2. если шаг 0 или 1 напечатал «локальная конфигурация изменена, получено объектов из хранилища: N» —
выгрузи названные объекты: /db-dump-xml <база> <каталог> -Mode Partial -ObjectsFile "<файл из вывода>"
3. правки в исходниках: /meta-edit, /form-edit, /skd-edit, /meta-compile и т. д.
4. /db-load-xml <каталог> <база> -Mode Partial -Files "Catalogs/Номенклатура.xml,…" -UpdateDB
5. /db-repo commit <база> -Objects "Справочник.Номенклатура" -Comment "…"
Шаг 0 стоит делать всегда, когда работа не продолжается сразу после предыдущего цикла: правки должны опираться на актуальное состояние — в том числе тех объектов, которые ты не меняешь, но используешь.
Шаг 2 пропускать нельзя: захват и обновление подтягивают из хранилища свежие версии, и загрузка исходников, снятых раньше, откатит чужие изменения — молча, без ошибки.
Что вообще захватывается. Отдельные объекты хранилища — сам объект, а также его формы, макеты и команды. Реквизиты, табличные части, измерения и ресурсы отдельными объектами не являются: они правятся в составе владельца.
| Что правишь | Что захватывать |
|---|---|
| Реквизит, табличную часть, измерение, ресурс, модуль объекта | сам объект: Справочник.Контрагенты |
| Существующую форму, макет, команду | её саму: Справочник.Контрагенты.Форма.ФормаЭлемента |
| Добавляешь новую форму, макет, команду | объект-владельца; при помещении назови и новый объект |
| Добавляешь новый объект конфигурации | только корень: Конфигурация. Самого объекта ещё нет — захватить его нельзя; при помещении назови и его |
What ships with it
6 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.
- 13d ago First seen · 201 lines · 56 tokens per session scan A 23b4365de69a
db-repo is a skill published in the GitHub repository Nikolay-Shirokov/cc-1c-skills (595 stars, last pushed 5d ago), licensed MIT. It adds 56 tokens to every session and 2,888 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 2026-08-30.
Other skills, from other repositories
1c-db-load-git
A tool for loading changed 1C configuration files from Git into a 1C information base. Git is a system that records file changes, while an information base is the running application data and configuration.
1c-db-load-git
A tool that finds changed 1C configuration files in Git and loads only those changes into an information base. 1C is a business application platform, and an information base is its database and configuration.
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.
1c-storage-ops
A set of command-line operations for the 1C configuration repository, including version status, object locks, updates, commits, exports, and database connections. The repository is 1C's own shared configuration history and is separate from Git.
doris-repo-review
Review an Apache Doris PR from a local clone with the same multi-agent, shared-ledger convergence workflow as the CI Code Review Runner. Use when the user supplies a PR to /doris-repo-review, asks to review a Doris PR locally, or asks for the CI-style review flow. Safely align only the current worktree to the exact PR…
1c-db-create
A tool that creates a new 1C information base, either as files on a computer or as a database on a server. An information base is the 1C database that stores an organisation’s configuration and data.