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 AzeevAN/mcp-1c --skill bslfmtgit clone --depth 1 https://github.com/AzeevAN/mcp-1cWrote 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/azeevan/mcp-1c/bslfmt)<a href="https://agentmods.dev/skills/azeevan/mcp-1c/bslfmt"><img src="https://agentmods.dev/badge/skills/azeevan/mcp-1c/bslfmt/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/azeevan/mcp-1c/bslfmt"><img src="https://agentmods.dev/badge/skills/azeevan/mcp-1c/bslfmt.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 | $0.00067 | $0.02052 |
| Opus 5.5 | $0.00027 | $0.00821 |
| Sonnet 5.5 | $0.00013 | $0.00410 |
| Haiku 4.5 | $0.00007 | $0.00205 |
Grade A, and why
bslfmt 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.
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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Форматирование BSL через bslfmt
Версия skill: 0.3.0. Закреплённая версия утилиты: bslfmt 0.27.0.
MCP не требуется.
Когда применять
Используй локальную утилиту, если пользователь просит отформатировать BSL-файл или полный текст отдельной процедуры/функции, в том числе после правки кода. Вход — локальный путь либо доступный агенту текст. Результат — изменённый файл в разрешённой области либо форматированный текст, если запись не запрошена.
Не используй skill как доказательство компиляции, корректности API или поведения кода. Не запрашивай целый модуль у удалённого MCP-сервера только ради форматирования и не передавай ему локальный путь или исходный текст. Если нет локального файла или текста, сообщи, какой вход отсутствует.
Подготовка утилиты
Утилите нужен Python 3.10+. Проверь установленную версию: bslfmt --version.
Правила ниже описаны для закреплённой версии 0.27.0; выпуски 0.x
несовместимо меняют вывод, поэтому новая версия не берётся молча. Сверка
локальная, без сетевых запросов:
- версия совпадает — продолжай;
- установленная старше или утилиты нет — установи закреплённую командой ниже;
- установленная новее — сообщи пользователю, что её вывод может отличаться
от описанного здесь, и предложи разовый запуск закреплённой версии через
uvx(см. ниже); новую используй только с его согласия.
Наличие более нового релиза проверяй только по просьбе пользователя, одним
запросом: gh release view --repo AzeevAN/bslfmt --json tagName,publishedAt
(без gh — pip index versions bslfmt). Сообщи номер и ссылку на заметки
релиза; закреплённую версию в skill не меняй — переход на новую решает
пользователь после чтения изменений вывода и команд.
На 2026-10-02 последний релиз GitHub
и версия на PyPI — 0.27.0.
Устанавливай конкретный тег GitHub:
uv tool install --from 'git+https://github.com/AzeevAN/[email protected]' bslfmt
bslfmt --version
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.
- 5d ago Changed · +29 lines fc3f1abb58f1
- 15d ago Changed · +17 lines 474979290d9c
- 18d ago First seen · 103 lines · 67 tokens per session scan A 873e0f934191
bslfmt is a skill published in the GitHub repository AzeevAN/mcp-1c (10 stars, last pushed 6d ago), licensed Apache-2.0. It adds 67 tokens to every session and 2,052 once invoked, about $0.0003 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 2026-09-29.
Other skills, from other repositories
v8unpack-cf
A Python tool for unpacking and rebuilding 1C configuration files (CF, CFE, and EPF) as readable JSON and BSL source files. 1C is a business software platform widely used in Russian-speaking companies.
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.
transcribe
A tool for turning video and audio recordings into written text, with optional speaker identification and video analysis.
1c-form-compile
A builder for managed 1C forms, the screens users work with in the 1C business-software platform. It creates the Form.xml file from a JSON description or from an object's metadata.
1c-web-test
A browser-automation tool for testing the 1C:Enterprise web client. It uses scripted actions to navigate screens, fill forms, read tables and reports, and apply filters.