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 agentmods add instructions/desko77/1c-formsserver/claude-mdgit clone --depth 1 https://github.com/Desko77/1c-formsserverWrote 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/instructions/desko77/1c-formsserver/claude-md)<a href="https://agentmods.dev/instructions/desko77/1c-formsserver/claude-md"><img src="https://agentmods.dev/badge/instructions/desko77/1c-formsserver/claude-md.svg" alt="Measured on agentmods" 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 | $0.01268 | $0.01268 |
| Opus 5 | $0.00634 | $0.00634 |
| Sonnet 5 | $0.00254 | $0.00254 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade A, and why
1c-formsserver CLAUDE.md 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 4d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1c-formsserver
MCP-сервер для работы с управляемыми формами 1С (Form.xml / Form.form).
DONE: EDT-дефолты и валидация (реализовано)
Трехслойная защита от пропуска EDT-свойств агентом. Дополнено 2026-03-28: маппинг типов Object, стрип v8:, дефолты таблиц (16 свойств), 3 новых правила MANDATORY-чеклиста (типы, autoCommandBar, view/edit).
1. get_form_prompt - добавить MANDATORY-чеклист в начало промпта
В самом начале ответа (ДО JSON, ДО примеров) добавить короткий императивный блок. Короткие правила в начале имеют больший "вес" для агента, чем свойства на 200-й строке JSON.
**MANDATORY - НИКОГДА НЕ ПРОПУСКАТЬ:**
1. Каждый InputField -> extInfo ОБЯЗАН содержать:
chooseType, typeDomainEnabled, textEdit (даже если true по умолчанию)
2. Каждый FormField в таблице -> ОБЯЗАН содержать:
editMode (EnterOnInput), showInHeader (true),
headerHorizontalAlign (Left), showInFooter (true)
3. Handlers InputField - РАЗМЕЩЕНИЕ:
- В <extInfo> (как <handlers>): StartChoice, Clearing, Opening,
ChoiceProcessing, AutoComplete, TextEditEnd
- На уровне элемента (<Events>): OnChange, Drag*
4. Button вне CommandBar -> type ОБЯЗАН быть UsualButton
Button в CommandBar -> type = CommandBarButton (дефолт, можно не указывать)
5. Имя кнопки = имя команды (НЕ "Кнопка" + имя, НЕ имя + "Кнопка")
6. НЕ добавлять containedObjects с classId вручную - EDT добавляет сам
7. НЕ дублировать title, если он совпадает с именем реквизита - платформа подставит автоматически
8. Предпочитать встроенную кнопку выбора (choiceButton + StartChoice)
вместо отдельной кнопки рядом с полем
Файл: src/mcp_forms/server.py, тулза get_form_prompt.
Где вставить: в начало строки result, перед ## Дополнение контекста.
2. generate_form - автоматические EDT-дефолты
При генерации формы сервер должен гарантированно добавлять дефолтные свойства, даже если пользователь их не указал.
InputFieldExtInfo - всегда добавлять:
autoMaxWidth: trueautoMaxHeight: truechooseType: truetypeDomainEnabled: truetextEdit: true
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.
- 4d ago First seen · 108 lines · 1,268 tokens per session scan A 657b2a972aca
1c-formsserver CLAUDE.md is an instructions file published in the GitHub repository Desko77/1c-formsserver (9 stars, last pushed 5mo ago), licensed MIT. It adds 1,268 tokens to every session, about $0.0063 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 2026-08-31.
Other instructions, from other repositories
1c-ssl-skills CLAUDE.md
Instructions for brake71/1c-ssl-skills, covering инструкции для ai-агентов, назначение репозитория, структура, локальные источники бсп and работа со скилом.
1c_hbk_bsl AGENTS.md
Instructions for mussolene/1c_hbk_bsl, covering oacs / acs repository workflow and repository python runtime.
1c_hbk_bsl CLAUDE.md
Instructions for mussolene/1c_hbk_bsl: Use OACS/ACS for substantial repository work as the governed local context, evidence, and checkpoint layer. OACS records facts and proof; it does not choose or run tools for the assistant.
1c-ai-development-kit CLAUDE.md
Claude Code instructions for Arman-Kudaibergenov/1c-ai-development-kit, covering 1c ai workspace — claude code configuration, о проекте, структура, mandatory: mcp-first rule and when to use which mcp tool (in 1c projects).
1c-feature-dev CLAUDE.md
Claude Code instructions for Diversus23/1c-feature-dev, covering claude.md, что это, архитектура, ключевые потоки данных and правила кодирования 1с (из rules/1c-rules.md).
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).