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 meta-decompilegit 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/meta-decompile)<a href="https://agentmods.dev/skills/nikolay-shirokov/cc-1c-skills/meta-decompile"><img src="https://agentmods.dev/badge/skills/nikolay-shirokov/cc-1c-skills/meta-decompile/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/meta-decompile"><img src="https://agentmods.dev/badge/skills/nikolay-shirokov/cc-1c-skills/meta-decompile.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 | $0.00059 | $0.00911 |
| Opus 5 | $0.00030 | $0.00456 |
| Sonnet 5 | $0.00012 | $0.00182 |
| Haiku 4.5 | $0.00006 | $0.00091 |
Grade A, and why
meta-decompile 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 11d 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-meta-decompile — 88% identical, 26 lines differ
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/meta-decompile — DSL-заготовка из XML объекта метаданных
Читает XML объекта метаданных (Catalogs/Имя.xml и т.п.) и эмитит компактный JSON в формате /meta-compile. Назначение — взять существующий объект образцом и собрать по нему НОВЫЙ: декомпилировать → поправить → скомпилировать под другим именем.
⚠️ Главное: это НЕ обратимая выгрузка
Компиляция черновика создаёт новый объект с новой идентичностью, а не копию исходного. В JSON не попадают: UUID (идентичность самого объекта и всех дочерних), тела модулей, формы, макеты, права. Захватываются только структура и свойства.
Отсюда правило: никогда не компилируй черновик поверх объекта-источника и не выдавай его за «реимпорт» — у пересобранного объекта другие UUID, поэтому все ссылки на исходный объект (из кода, других объектов, состава подсистем, предопределённых данных) сломаются, а код модулей и формы пропадут.
Когда использовать
Собрать новый объект по образцу существующего — получить DSL-заготовку рабочего объекта, переименовать и адаптировать состав, скомпилировать в новый. Быстрее, чем писать DSL с нуля для богатого объекта.
Когда не использовать
- Точечная правка существующего объекта (добавить реквизит, ТЧ, свойство) →
/meta-edit. Цикл decompile→compile тут вреден: даёт объект с новой идентичностью и теряет модули/формы. - Сохранить / восстановить / перенести тот же объект (бэкап, миграция между конфигурациями с сохранением ссылок) → штатная выгрузка 1С (
/db-dump-xml↔/db-load-xml, CF), а не decompile. - Просто понять структуру объекта (реквизиты, ТЧ, типы) без пересборки →
/meta-info(дешевле, не плодит файл).
Параметры
| Параметр | Описание |
|---|---|
ObjectPath |
Путь к XML объекта (Catalogs/Имя.xml), обязательный |
OutputPath |
Путь к выходному JSON. Если не задан — JSON в stdout |
powershell.exe -NoProfile -File "${CLAUDE_SKILL_DIR}/scripts/meta-decompile.ps1" -ObjectPath "<Объект.xml>" -OutputPath "<out.json>"
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.
- 11d ago First seen · 53 lines · 59 tokens per session scan A 1f526baeef40
meta-decompile is a skill published in the GitHub repository Nikolay-Shirokov/cc-1c-skills (591 stars, last pushed 4d ago), licensed MIT. It adds 59 tokens to every session and 911 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
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.
1c-feature-dev
A development guide for adding or changing functionality in 1C, a business software platform widely used for accounting, finance, and enterprise operations.
1c-docs
A documentation-writing skill for 1C code. 1C is a business software platform commonly used for accounting, inventory, and other company operations.
brainstorm
A planning guide for creative software work, such as features, components, and behavior changes.
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.
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.