1c77-dev

1c77-dev is a skill for Claude Code, Codex from Desko77/cursor-1c-skills. It costs 6 tokens per session (1,883 once invoked), scanned A, a copy of 1c77-dev, MIT.

A development guide for 1C:Enterprise 7.7, an older version of the 1C business-application platform. It covers the version's code, forms, metadata, binary files, encoding, and command-line tools.

In plain words
What is it for?
Use it to modify 1C 7.7 code, forms, metadata, and external data processors while handling its older syntax, file formats, and Windows-1251 text encoding.
Why use it?
1C 7.7 works differently from newer 1C versions, so techniques for 1C 8.x can produce invalid code or unreadable files.

Skill for Claude CodeCodex

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

Good fit Use it to modify 1C 7.7 code, forms, metadata, and external data processors while handling its older syntax, file formats, and Windows-1251 text encoding.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/desko77/cursor-1c-skills/1c77-dev
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/cursor-1c-skills --skill 1c77-dev
Clone the repo
git clone --depth 1 https://github.com/Desko77/cursor-1c-skills

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 1c77-dev

README.md
[![agentmods](https://agentmods.dev/badge/skills/desko77/cursor-1c-skills/1c77-dev/github.svg)](https://agentmods.dev/skills/desko77/cursor-1c-skills/1c77-dev)
Your own site
<a href="https://agentmods.dev/skills/desko77/cursor-1c-skills/1c77-dev"><img src="https://agentmods.dev/badge/skills/desko77/cursor-1c-skills/1c77-dev/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 1c77-dev

Your own site · 80×15
<a href="https://agentmods.dev/skills/desko77/cursor-1c-skills/1c77-dev"><img src="https://agentmods.dev/badge/skills/desko77/cursor-1c-skills/1c77-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,883 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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 content
    Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
How audits are shown
Origin 94% copy Near-identical to another mod 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 $0.00006 $0.01883
Opus 5 $0.00003 $0.00941
Sonnet 5 $0.00001 $0.00377
Haiku 4.5 $0.00001 $0.00188

Measured 5d ago against content hash ac128f7489b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

1c77-dev 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 5d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/analyze_module.py, scripts/build_ert.py, scripts/cp1251_io.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.

Origin

This is a copy

94% identical to 1c77-dev — 63 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/1c77-dev/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Разработка под 1С 7.7 (1c77-dev)

Доработка кода, форм, метаданных и внешних обработок 1С:Предприятия 7.7. Версия 7.7 кардинально отличается от 8.x, и привычные для 8.x приемы тут ломаются. Этот скилл собирает рабочие приемы, особенности синтаксиса и готовые скрипты.

Чем 7.7 отличается (читать обязательно)

  • Нет EDT и .bsl/.mdo. Конфигурация хранится в бинарном 1Cv7.MD, внешние обработки - в бинарном .ert. Редактируемые исходники получают разбором через GComp (текстовые .1s, .frm, .mdp, .mxl).
  • Кодировка везде CP1251. Файлы .1s/.frm/.mdp - не UTF-8. Инструмент Grep (ищет по UTF-8-байтам) кириллицу в них не находит. Read показывает кракозябры. Читать/править - только через Python с encoding='cp1251' (см. scripts/cp1251_io.py) либо через MCP-сервер 1c77-metadata.
  • Синтаксис строже и беднее 8.x. Нет типа Булево; число в условии Если не приводится к логическому; многих функций 8.x (ЗначениеЗаполнено, штатной ПустаяСтрока как Булево) нет или ведут себя иначе. Это источник большинства ошибок компиляции. Подробно: references/syntax-gotchas-77.md.

Карта навигации

Читай нужный файл по ситуации, не загружай все сразу:

Когда Файл
Пишешь/правишь BSL-код 7.7, ловишь ошибку компиляции "Выражение должно иметь логический тип" и т.п. references/syntax-gotchas-77.md
Нужно понять структуру .1s / .frm / .mdp / .mxl / .ert, что внутри обработки references/file-formats-77.md
Надо разобрать .ert в исходники или собрать обратно references/gcomp.md
Анализ метаданных конфигурации, поиск реквизита, проверка запроса 7.7, окружение references/mcp-and-tools.md

Скрипты в scripts/ (запуск с --help):

  • cp1251_io.py - чтение/запись/grep по .1s в CP1251 (когда обычный Grep слеп).
  • analyze_module.py - инвентаризация модуля: СоздатьОбъект, типы метаданных, глобальные гл*-функции, обращения к реквизитам.
  • patch_by_marker.py - идемпотентная вставка блока кода по маркеру-якорю (для повторяемых правок).
  • build_ert.py / unpack_ert.py - обертки GComp (сборка/разбор .ert) через PowerShell.

Read the full file on GitHub · 94 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. 5d ago First seen · 94 lines · 6 tokens per session scan A ac128f7489b0

Subscribe to this mod's changes

1c77-dev is a skill published in the GitHub repository Desko77/cursor-1c-skills (55 stars, last pushed 6d ago), licensed MIT. It adds 6 tokens to every session and 1,883 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to 1c77-dev, differing in 63 lines, and is treated as a copy.