agentmods.dev

bsl-ai-toolkit: Skill for Claude Code

.claude/skills/1c-metadata/SKILL.md

1c-metadata is a skill for Claude Code from vgtitov/bsl-ai-toolkit. It costs 192 tokens per session (2,371 once invoked), scanned A, original, MIT.

A tool for programmatically editing 1C:Enterprise metadata, forms, reports, queries, and related files while checking that changes can be exported and reloaded correctly.

In plain words
What is it for?
Use it to add fields, report queries, or print-form columns, work with Configurator XML or EDT files, validate round trips, and run checks after BSL code changes.
Why use it?
It keeps structural edits focused and verifies that the files remain unchanged except for the intended updates.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is vgtitov/bsl-ai-toolkit's own configuration. It tells Claude Code how to work on bsl-ai-toolkit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bsl-ai-toolkit configures →

not rated 21repo +7 changed 6d ago A scan SkillSpector: warn 192 tokens original MIT
View source ↗ vgtitov/bsl-ai-toolkit
Reuse

Borrowing it

Nothing to install: this file belongs to vgtitov/bsl-ai-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vgtitov/bsl-ai-toolkit/main/.claude/skills/1c-metadata/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vgtitov/bsl-ai-toolkit

Made for: Claude Code.

Wrote 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.

agentmods badge for 1c-metadata

README.md
[![agentmods](https://agentmods.dev/badge/skills/vgtitov/bsl-ai-toolkit/1c-metadata/github.svg)](https://agentmods.dev/skills/vgtitov/bsl-ai-toolkit/1c-metadata)
Your own site
<a href="https://agentmods.dev/skills/vgtitov/bsl-ai-toolkit/1c-metadata"><img src="https://agentmods.dev/badge/skills/vgtitov/bsl-ai-toolkit/1c-metadata/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.

agentmods 80×15 button for 1c-metadata

Your own site · 80×15
<a href="https://agentmods.dev/skills/vgtitov/bsl-ai-toolkit/1c-metadata"><img src="https://agentmods.dev/badge/skills/vgtitov/bsl-ai-toolkit/1c-metadata.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 192 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,371 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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 content
    Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00192 $0.02371
Opus 5 $0.00096 $0.01185
Sonnet 5 $0.00038 $0.00474
Haiku 4.5 $0.00019 $0.00237

Measured 6d ago against content hash 9a9109e40793, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

1c-metadata 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 6d 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.

.claude/skills/1c-metadata/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

1c-metadata — структурные правки метаданных 1С

Локализация (сначала, если есть)

Если в скилле есть каталог references/local/ — прочитай его ПЕРЕД работой: version-stack.md (версии платформы/библиотек, режим совместимости, префиксы ТВОЕЙ компании) и остальные карты. При противоречии локальное побеждает generic. Контракт — docs/SKILL_LOCALIZATION.md toolkit.

Ядро: onec_metadata/ (Python, lxml). CLI: bin/1c-meta. Каталог покрытия: onec_metadata/catalog.py — операции вне каталога делает человек в IDE.

Железные правила

  1. Только тест-база. Загрузка изменений — исключительно в тестовую ИБ (напр. localhost\<testbase>). В прод — человек, после приёмки.
  2. Round-trip обязателен. После загрузки: повторная выгрузка → diff с эталоном == строго целевые файлы (apply.dumpload.roundtrip_verify). Без чистого round-trip правка не считается выполненной.
  3. Минимальный дифф. Формат-слой (formats/configurator.py) даёт byte-perfect round-trip (BOM/CRLF/табы); операции меняют только целевые узлы. Никогда не переформатируй XML вручную/другими инструментами.
  4. BSL после правки кода — если задет *.bsl, прогони BSL Language Server.
  5. Смок-валидатор СКД (ENFORCED, офлайн) — после любой правки схемы компоновки: 1c-meta scd validate <Schema.xml> (exit 1 = поломка: пропал набор, поле без dataPath, дубль поля, битая связь наборов, невалидный XML). До загрузки в 1С.
  6. Класс поля СКД перед добавлением в группировку. Поле выводится в выбранных полях группировки, только если оно: поле группировки | реквизит поля группировки (dataPath через точку — Номенклатура.Артикул) | ресурс (totalField). Иначе — Поле ... не может быть использовано в группировке .... Для обычного (неагрегатного) атрибута правильный класс — реквизит, не ресурс: в структуре «Таблица» ресурсы уходят в ячейки на пересечении строк и колонок, а не в колонку строки. Перед правкой посмотреть, как объявлены уже работающие неагрегатные поля этой же группировки, и повторить их класс. Проверить РасположениеРеквизитов (умолчание «Вместе с владельцем» → колонки склеиваются с владельцем; для отдельных колонок нужно Отдельно). Подробно — references/skd-fields-in-groupings.md.
  7. Объект расширения в типовом интерфейсе — через ПодключаемыеОтчетыИОбработки. СведенияОВнешнейОбработке() работает ТОЛЬКО для внешних файлов .erf/.epf в справочнике ДополнительныеОтчетыИОбработки (БСП поднимает их из ХранилищеОбработки через ВнешниеОтчеты.Создать). Для отчёта/обработки ВНУТРИ расширения она не вызывается никогда. Штатный путь: заимствовать подсистему ПодключаемыеОтчетыИОбработки, включить в её состав свой объект, в модуле менеджера определить ПриОпределенииНастроек + парную процедуру (ДобавитьКомандыПечати / ДобавитьКомандыОтчетов / НастроитьВариантыОтчета / ДобавитьКомандыЗаполнения / ДобавитьКомандыСозданияНаОсновании). Подробно, включая рецепт печатной формы с макетом Word — references/bsp-extension-attachable-objects.md.
  8. Scope-guard «не тронул незатронутое» (ENFORCED, офлайн) — property-level diff onec_metadata/apply/scope_guard.assert_in_scope(before, after, scope) БЕЗ тест-базы блокирует дрейф свойств у объектов, которые правка менять не должна была (дополняет файловый roundtrip_verify до уровня свойств).

Read the full file on GitHub · 108 lines

Files

What ships with it

4 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.

Changes

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.

  1. 6d ago Changed · +7 lines 9a9109e40793
  2. 10d ago First seen · 101 lines · 192 tokens per session scan A d427f31c9e00

Subscribe to this mod's changes

1c-metadata is a skill published in the GitHub repository vgtitov/bsl-ai-toolkit (21 stars, last pushed 2d ago), licensed MIT. It adds 192 tokens to every session and 2,371 once invoked, about $0.0010 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.

1c1c-enterpriseClaude Codeaibslclaude
Related

Other skills, from other repositories

bsp

A guide for developing and reviewing business software in 1C with its Standard Subsystems Library, a collection of shared building blocks for common tasks.

brake71/1c-ssl-skills · 157 tokens

docx-from-sample

A document-building tool that creates a new DOCX file using an existing DOCX as its formatting template. DOCX is the file format used by Microsoft Word.

Desko77/cursor-1c-skills · 115 tokens

1c-bsp-registration

A helper for 1C external reports and processors that adds the function needed to register them in the Standard Subsystems Library (БСП). БСП is a set of reusable features for 1C configurations.

Desko77/cursor-1c-skills · 27 tokens

claude-md-bootstrap

A project setup tool that creates or updates a CLAUDE.md file, which gives an AI coding agent project-specific instructions and background at the start of each session.

Desko77/cursor-1c-skills · 6 tokens

1c-cfe-patch-method

A tool for creating method interceptors in a 1C configuration extension. 1C is business software, and an interceptor can run code before, after, or instead of an inherited method.

Desko77/cursor-1c-skills · 61 tokens

1c-mxl-info

A structure reader for 1C spreadsheet-layout files. It summarizes named regions, parameters, and column sets instead of showing the full XML.

Desko77/cursor-1c-skills · 47 tokens