edt-bsl-write-safety

edt-bsl-write-safety is a cursor rule for Cursor from Desko77/cursor-1c-skills. It costs 0 tokens per session (1,505 once invoked), scanned A, original, MIT.

Rules for safely editing BSL modules through the 1C development environment's editing interface. BSL is the programming language used by the 1C platform, and the rules distinguish small edits from replacing an entire module.

In plain words
What is it for?
Use it when changing BSL source with the module-writing tool. It covers replacing methods or lines, inserting text, appending code, and protecting edits with expected text.
Why use it?
It reduces the chance of overwriting a whole module or losing code through an overly broad edit. It also requires checking the syntax errors returned after a write.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use it when changing BSL source with the module-writing tool. It covers replacing methods or lines, inserting text, appending code, and protecting edits with expected text.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/desko77/cursor-1c-skills/edt-bsl-write-safety
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.

Clone the repo
git clone --depth 1 https://github.com/Desko77/cursor-1c-skills

Made for: Cursor.

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 edt-bsl-write-safety

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

Your own site · 80×15
<a href="https://agentmods.dev/rules/desko77/cursor-1c-skills/edt-bsl-write-safety"><img src="https://agentmods.dev/badge/rules/desko77/cursor-1c-skills/edt-bsl-write-safety.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,505 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 $0.00000 $0.01505
Opus 5 $0.00000 $0.00753
Sonnet 5 $0.00000 $0.00301
Haiku 4.5 $0.00000 $0.00151

Measured 10d ago against content hash b2304e563b74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

edt-bsl-write-safety 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.

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.

rules/edt-bsl-write-safety.mdc · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Безопасная запись BSL через write_module_source

Самая опасная зона при работе с кодом 1С через EDT MCP: неверный режим записи может затереть весь модуль или потерять часть кода. Прочитать ДО первой записи в модуль.

Применяется: при записи BSL через write_module_source (ai-edt). Дополняет file-edit-efficiency.md (выбор инструмента) и mcp-tool-priority.md (маршрут и обязательные проверки).


Режимы write_module_source и их риск

Режим Что делает Риск
searchReplace Находит фрагмент и заменяет. Затрагивает только найденное Низкий - режим по умолчанию для точечной правки
replaceMethod Заменяет один метод целиком по имени Низкий - безопасен для правки метода
replaceLines Заменяет диапазон строк (с защитой expectedText) Средний - см. ниже
insertBefore / insertAfter Вставка относительно якоря Низкий
append Добавляет в конец модуля Низкий
replace Перезаписывает ВЕСЬ файл модуля Высокий - см. правило 1

После записи EDT автоматически валидирует результат (синтаксис) и возвращает ошибки в ответе - проверять их сразу.


Правило 1: НИКОГДА не использовать replace для одного метода

replace заменяет весь файл модуля. Передав один метод - удалишь весь остальной код (сотни/тысячи строк), без отката.

Для правки одного метода - replaceMethod (по имени) или searchReplace (старый текст метода в поиск, новый в замену). replace оправдан только когда: модуль создается впервые, либо модуль пустой/менее ~50 строк и передается его полное содержимое, либо полная перезапись модуля по явному согласованию с пользователем.

Правило 2: oldSource (searchReplace) = доказательство, что прочитал текущий код

Для searchReplace искомый фрагмент должен встречаться в файле РОВНО один раз. Ноль совпадений - операция отклонена; больше одного - тоже отклонена с подсказкой взять более крупный уникальный фрагмент. Это защищает от замены не того места и подтверждает, что ты видел актуальное содержимое. При ошибке "not found / multiple" - НЕ ретраить вслепую: перечитать метод (read_method_source) и обновить/расширить искомый фрагмент до уникального.

Read the full file on GitHub · 83 lines

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 · 83 lines · 0 tokens per session scan A b2304e563b74

Subscribe to this mod's changes

edt-bsl-write-safety is a cursor rule published in the GitHub repository Desko77/cursor-1c-skills (55 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,505 tokens. 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.