meta-compile

meta-compile is a skill for Claude Code from timoshinoleg-eng/1c-ai-workbench. It costs 48 tokens per session (1,229 once invoked), scanned A, original, MIT.

A generator for 1C configuration objects, such as directories, documents, registers, reports, and shared modules, from a JSON definition.

In plain words
What is it for?
Use it to create or add 1C metadata objects from one JSON file, including their configuration structure and generated modules.
Why use it?
It removes the need to hand-write the XML and module files that make up a 1C configuration object or manually register them in the configuration.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the 1c-skills plugin — 71 skills, 2 hooks shipped together

Good fit Use it to create or add 1C metadata objects from one JSON file, including their configuration structure and generated modules.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/timoshinoleg-eng/1c-ai-workbench/meta-compile
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 timoshinoleg-eng/1c-ai-workbench --skill meta-compile
Clone the repo
git clone --depth 1 https://github.com/timoshinoleg-eng/1c-ai-workbench

Made for: Claude Code.

Or install 1c-skills, the plugin that ships this one along with the rest of its 71 skills, 2 hooks.

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 meta-compile

README.md
[![agentmods](https://agentmods.dev/badge/skills/timoshinoleg-eng/1c-ai-workbench/meta-compile/github.svg)](https://agentmods.dev/skills/timoshinoleg-eng/1c-ai-workbench/meta-compile)
Your own site
<a href="https://agentmods.dev/skills/timoshinoleg-eng/1c-ai-workbench/meta-compile"><img src="https://agentmods.dev/badge/skills/timoshinoleg-eng/1c-ai-workbench/meta-compile/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 meta-compile

Your own site · 80×15
<a href="https://agentmods.dev/skills/timoshinoleg-eng/1c-ai-workbench/meta-compile"><img src="https://agentmods.dev/badge/skills/timoshinoleg-eng/1c-ai-workbench/meta-compile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,229 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.
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 $0.00048 $0.01229
Opus 5 $0.00024 $0.00615
Sonnet 5 $0.00010 $0.00246
Haiku 4.5 $0.00005 $0.00123

Measured 10d ago against content hash 35fd20ea792b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

meta-compile 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 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/meta-compile.ps1, scripts/meta-compile.py), 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.

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.

tools/cc-1c-skills/.claude/skills/meta-compile/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/meta-compile — генерация объектов метаданных из JSON DSL

Принимает JSON-определение объекта метаданных → генерирует XML + модули в структуре выгрузки конфигурации + регистрирует в Configuration.xml.

Порядок работы

  1. Составь JSON по синтаксису и примерам ниже → запиши во временный файл
  2. Запусти скрипт meta-compile
  3. Если нужно изменить созданный объект — /meta-edit
  4. Если нужно проверить — /meta-validate

Команда

powershell.exe -NoProfile -File "${CLAUDE_SKILL_DIR}/scripts/meta-compile.ps1" -JsonPath "<json>" -OutputDir "<ConfigDir>"
Параметр Описание
JsonPath Путь к JSON-файлу (один объект {...} или массив [{...}, ...])
OutputDir Корень выгрузки конфигурации (где Configuration.xml, Catalogs/, Documents/ и т.д.)

JSON DSL

Общая структура

{ "type": "Catalog", "name": "Номенклатура", ...свойства типа... }

type и name — обязательные. synonym генерируется из name автоматически (CamelCase → слова через пробел). Можно задать явно: "synonym": "Мой синоним".

Shorthand реквизитов

Используется в attributes, dimensions, resources, tabularSections:

"ИмяРеквизита"                    → String(10) по умолчанию
"ИмяРеквизита: Тип"               → с типом
"ИмяРеквизита: Тип | req, index"  → с флагами

Типы: String(100), Number(15,2), Boolean, Date, DateTime, CatalogRef.Xxx, DocumentRef.Xxx, EnumRef.Xxx, DefinedType.Xxx и др. ссылочные.

Составной тип: "Значение: String + Number(15,2) + CatalogRef.Контрагенты".

Флаги: req, index, indexAdditional, nonneg, master, mainFilter, denyIncomplete, useInTotals.

Свойства по типам

Примеров и shorthand-синтаксиса выше достаточно для типовых задач. Если нужны свойства типа, не показанные в примерах, и их допустимые значения — см. reference-файл:

  • reference/types-basic.md — Catalog, Document, Enum, Constant, DefinedType, Report, DataProcessor
  • reference/types-registers.md — InformationRegister, AccumulationRegister, AccountingRegister, CalculationRegister, ChartOfAccounts, ChartOfCharacteristicTypes, ChartOfCalculationTypes
  • reference/types-process.md — BusinessProcess, Task, ExchangePlan, CommonModule, ScheduledJob, EventSubscription, DocumentJournal
  • reference/types-web.md — HTTPService, WebService

Read the full file on GitHub · 120 lines

Files

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.

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. 10d ago First seen · 120 lines · 48 tokens per session scan A 35fd20ea792b

Subscribe to this mod's changes

meta-compile is a skill published in the GitHub repository timoshinoleg-eng/1c-ai-workbench (0 stars, last pushed 23d ago), licensed MIT. It adds 48 tokens to every session and 1,229 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 2026-08-31.

Related

Other skills, from other repositories

onec-selective-export

Export and inspect only the 1C:Enterprise configuration metadata objects required for a task using Designer /DumpConfigToFiles -listFile. Use when asked to study a configuration, locate BSL logic, inspect a catalog, document, register, form, command, or module, or gather dependencies without dumping the whole…

Muredsa/1C-Enterprise-Agent-Toolkit · 70 tokens

onec-dev

Route safe 1C:Enterprise development work involving an infobase, configuration metadata, selective object export, configuration extensions, Designer batch mode, BSL changes, or extension testing. Use this as the entry point when a request spans several 1C workflows or does not clearly match one focused 1C skill.

Muredsa/1C-Enterprise-Agent-Toolkit · 67 tokens

onec-extension-lifecycle

Create, dump, edit, load, back up, roll back, and delete one named 1C:Enterprise configuration extension while preserving the main configuration. Use for .cfe files, extension source trees, new customization extensions, or changes to an existing extension.

Muredsa/1C-Enterprise-Agent-Toolkit · 59 tokens

onec-extension-validate

Validate a named 1C:Enterprise configuration extension through BSL module checks, full configuration checks, applicability checks, database update, and database .cfe verification. Use after creating or modifying an extension, when diagnosing why an extension cannot be applied, or before declaring extension work…

Muredsa/1C-Enterprise-Agent-Toolkit · 63 tokens

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.

Desko77/claude-code-skills-1c · 174 tokens

humanize-ai-text

A writing aid for rewriting text produced by language-model agents into a more natural human style. It keeps the original meaning, facts, numbers, and technical terms.

Desko77/claude-code-skills-1c · 329 tokens