agentmods.dev

kd31-rules

kd31-rules is a skill for Claude Code, Codex from Desko77/claude-code-skills-1c. It costs 291 tokens per session (2,709 once invoked), scanned B, original, MIT.

A guide for working with 1C Data Conversion 3.1 through an HTTP API. 1C is a business software platform, and EnterpriseData is its standard format for exchanging data between systems.

In plain words
What is it for?
It helps create and edit conversion rules, inspect metadata and format versions, and generate code or XSD files for EnterpriseData extensions.
Why use it?
It gives an agent rules for inspecting and changing data-conversion settings in a live 1C information base.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 60repo +6 7d ago B scan 291 tokens original MIT

Good fit It helps create and edit conversion rules, inspect metadata and format versions, and generate code or XSD files for EnterpriseData extensions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/desko77/claude-code-skills-1c/kd31-rules
View source ↗ Desko77/claude-code-skills-1c
Install

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.

Any agent
npx skills add Desko77/claude-code-skills-1c --skill kd31-rules
Clone the repo
git clone --depth 1 https://github.com/Desko77/claude-code-skills-1c

Made for: Claude Code, Codex.

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 kd31-rules

README.md
[![agentmods](https://agentmods.dev/badge/skills/desko77/claude-code-skills-1c/kd31-rules/github.svg)](https://agentmods.dev/skills/desko77/claude-code-skills-1c/kd31-rules)
Your own site
<a href="https://agentmods.dev/skills/desko77/claude-code-skills-1c/kd31-rules"><img src="https://agentmods.dev/badge/skills/desko77/claude-code-skills-1c/kd31-rules/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 kd31-rules

Your own site · 80×15
<a href="https://agentmods.dev/skills/desko77/claude-code-skills-1c/kd31-rules"><img src="https://agentmods.dev/badge/skills/desko77/claude-code-skills-1c/kd31-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 291 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,709 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00291 $0.02709
Opus 5 $0.00146 $0.01354
Sonnet 5 $0.00058 $0.00542
Haiku 4.5 $0.00029 $0.00271

Measured 6d ago against content hash fc4b9f055a81, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

kd31-rules scanned grade B with 2 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/kd31_exec.sh, scripts/kd31_query.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

Оба: payload через jq (fallback python) + `curl --data-binary @файл`, порт через

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Claude (агент) --Bash+curl (payload через jq/python в файл)--> MCP-toolkit (КД 3.1, СЕРВЕРНЫЙ контекст)
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/kd31-rules/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KD 3.1 - правила обмена EnterpriseData через MCP-toolkit

Скилл описывает работу с живой ИБ "Конвертация данных, редакция 3.1" (КД 3.1) через MCP-toolkit HTTP API: исследование структуры правил, создание/правка правил, настройка формата и получение артефактов для расширения формата EnterpriseData - модуля менеджера обмена (общий модуль BSL) и XDTO-пакета расширения / версии формата (XSD).

Относится к сборке КД 3.1.6.14 (платформа 8.5.1.1302).

Модель данных: КД 3.1 близка к КД 2.0 + слой формата

В этой сборке КД 3.1 по структуре похожа на КД 2.0:

  • Теневая модель метаданных: Релизы (версия загруженной структуры) -> Объекты (Владелец=Релизы) -> Свойства/Значения (Владелец=Объекты). Конфигурации - топ-контейнер, на который ссылаются Релизы (версии живут в Релизах).
  • Правила в справочниках: ПравилаКонвертацииОбъектов (ПКО), ПравилаКонвертацииСвойств (ПКС, Владелец=ПКО - это справочник, не регистр), ПравилаКонвертацииПредопределенныхДанных (ПКПД), ПравилаОбработкиДанных (ПОД), ПравилаРегистрацииОбъектов (ПРО, Владелец=Регистрации). ПКО/ПОД/ПКПД - топ-уровневые (без Владельца), связь с конвертацией - через СоставыКонвертаций. ВАЖНО: у ПКО нет реквизита Наименование (идентификатор в Коде, искать НайтиПоКоду) и ПКО НЕ иерархичен (нет ЭтоГруппа); ПКС иерархичен. Паттерн заполнения - 2 ПКО на объект (<Объект>_Отправка + <Объект>_Получение), эталон в демо. См. bsl-templates.md.
  • Дополнительно - слой формата EnterpriseData (цепочка справочников): ВерсииФормата (ПространствоИмен, признак расширения) -> ОбъектыФормата (Владелец=ВерсииФормата) -> СвойстваФормата -> ЗначенияФормата; типы - ТипыФормата.

Отличие результата от КД 2.0: КД 3.1 генерирует модуль менеджера обмена (BSL) для движка ОбменДаннымиXDTO плюс работает с XDTO-пакетом/версией формата, а не выгружает XML-правила для "Универсального обмена". Для КД 2.0 - скилл kd2-rules.

Архитектура работы

Claude (агент)  --Bash+curl (payload через jq/python в файл)-->  MCP-toolkit (КД 3.1, СЕРВЕРНЫЙ контекст)
   -> справочники Конвертации/ПКО/ПКС/ПКПД/ПОД + теневая модель + слой формата
   -> штатные обработки (ЗагрузкаСтруктурыКонфигурацииИзФайловXML, НастройкаПравилОбмена, ВыгрузкаМодуля)
   -> артефакты: CommonModule (менеджер обмена) + XDTOPackage/XSD расширения
   -> перенос в расширение конфигурации-приемника (например УНФ)

Read the full file on GitHub · 133 lines

Files

What ships with it

7 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 First seen · 133 lines · 291 tokens per session scan B fc4b9f055a81

Subscribe to this mod's changes

kd31-rules is a skill published in the GitHub repository Desko77/claude-code-skills-1c (60 stars, last pushed 7d ago), licensed MIT. It adds 291 tokens to every session and 2,709 once invoked, about $0.0015 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

1c1c-development1c-edt1c-enterpriseBackend and APIsai-agentanthropic
Related

Other skills, from other repositories

1c-xdto-compile

A builder that creates a 1C XDTO package from an XML Schema (XSD). XDTO packages describe XML data structures used for integrations, web services, and external XML formats.

Desko77/cursor-1c-skills · 55 tokens

1c-xdto-decompile

A converter that turns a 1C XDTO package into a readable, editable XML Schema (XSD) file. XDTO is 1C's format for describing XML data used in integrations.

Desko77/cursor-1c-skills · 62 tokens

1c-subsystem-compile

A generator that creates a 1C subsystem—a section of the application menu—from a JSON definition. It writes the subsystem's XML files and registers it in the configuration or a parent subsystem.

Desko77/cursor-1c-skills · 46 tokens

1c-xdto-validate

A checker for XDTO packages in 1C:Enterprise. XDTO describes the structure and data types used when 1C exchanges data with external systems.

Desko77/cursor-1c-skills · 36 tokens

1c-db-run

A tool that opens a selected 1C information base in 1C:Enterprise user mode. User mode is the normal interface where people work with the application and its data.

Desko77/cursor-1c-skills · 35 tokens

1c-epf-dump

A tool that extracts a 1C external processing file (EPF or ERF) into readable XML source files. External processing files are add-ons that run inside a 1C application.

Desko77/cursor-1c-skills · 60 tokens