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.
git clone --depth 1 https://github.com/Desko77/cursor-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/rules/desko77/cursor-1c-skills/file-edit-efficiency)<a href="https://agentmods.dev/rules/desko77/cursor-1c-skills/file-edit-efficiency"><img src="https://agentmods.dev/badge/rules/desko77/cursor-1c-skills/file-edit-efficiency/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/rules/desko77/cursor-1c-skills/file-edit-efficiency"><img src="https://agentmods.dev/badge/rules/desko77/cursor-1c-skills/file-edit-efficiency.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00015 | $0.01139 |
| Opus 5.5 | $0.00006 | $0.00456 |
| Sonnet 5.5 | $0.00003 | $0.00228 |
| Haiku 4.5 | $0.00002 | $0.00114 |
Grade A, and why
file-edit-efficiency 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
File Edit Efficiency
Стратегия минимизации токенов при чтении и редактировании файлов.
Применяется: при любых операциях чтения/редактирования файлов.
Выбор инструмента по задаче
Массовые однотипные замены (N файлов, одинаковый паттерн)
Grep → sed → grep (все через Bash):
grep- найти текущие значения, убедиться в паттернеsed -i 's|old|new|'- заменить во всех файлах за один вызовgrep- проверить результат
Не использовать Read+Edit для каждого файла - Read загружает весь файл в контекст, Edit требует предварительный Read. На N файлах это 2N вызовов и весь контент в контексте.
Точечные правки (1-2 файла, нужна точность)
Read → Edit:
- Edit проверяет уникальность old_string - безопаснее чем sed
- Read нужен один раз, потом можно делать несколько Edit по тому же файлу
- Для больших файлов: Read с offset+limit вместо полного чтения
BSL-код в EDT-проектах (при наличии MCP)
MCP read_method_source → write_module_source:
- Читает/пишет конкретный метод, а не весь модуль (экономия на файлах 3000+ строк)
- write_module_source проверяет синтаксис автоматически
- Режимы: searchReplace, replace, append
Поиск информации
| Задача | Инструмент | Не использовать |
|---|---|---|
| Найти файл по имени/паттерну | Glob | Bash find, Agent |
| Найти строку в файлах | Grep | Bash grep/rg, Agent |
| Прочитать конкретный фрагмент | Read (offset+limit) | Read всего файла |
| Понять структуру большого модуля | MCP get_module_structure | Read всего файла |
| Широкий поиск по кодовой базе | Agent (Explore) | Серия Grep вручную |
Кликабельная ссылка на файл (Cursor/VSCode)
Предпочтительный способ - формат @-references: @путь/от/корня/workspace/файл.ext:начало-конец. Работает с кириллицей, не тратит токены на tool-вызов.
Примеры:
@src/CommonModules/МодульИмя/Module.bsl:1-1@МояКонфигурация/src/Catalogs/Контрагенты/ObjectModule.bsl:45-60
Когда @-references не подходит (путь вне workspace, например C:\Users\...) - fallback через tool-результат:
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.
- 1mo ago First seen · 88 lines · 15 tokens per session scan A 9457725723d0
file-edit-efficiency is a cursor rule published in the GitHub repository Desko77/cursor-1c-skills (69 stars, last pushed 11d ago), licensed MIT. It adds 15 tokens to every session and 1,139 once invoked, about $0.0001 per session on Opus 5.5. 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 cursor rules, from other repositories
jsdoc
A set of JSDoc rules for documenting JavaScript or TypeScript code, with comments written in Russian.
project-context
Technical context for a VS Code extension that exposes 1C Platform Tools to AI agents through an MCP server. The extension communicates with the standalone server over IPC, while the server registers one agent tool for each available 1C command.
naming-abbreviations
A set of project rules for naming 1C Platform Tools and its MCP tools. It defines allowed short forms and limits the combined server and tool name to 60 characters.
code-style
Project rules for code style, commit messages, comments, interface text, logs, TypeScript, and documentation. They require Russian text in user-facing and code-comment contexts, along with strict TypeScript practices.
evolution-no-legacy
A coding rule for changing software interfaces and configuration names without keeping old names working by default.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.