1confdb-knw: Instructions file for Claude Code

CLAUDE.md

1confdb-knw CLAUDE.md is an instructions file for Claude Code from Zom31C/1confdb-knw. It costs 2,464 tokens per session, scanned A, original, MIT.

Coding instructions for using 1confdb-knw, a read-only knowledge base for 1C:Enterprise configurations. 1C is a business-automation platform, and BSL is its built-in programming language.

In plain words
What is it for?
Use them when writing or reviewing 1C/BSL code or queries based on a specific configuration, and when connecting to the local knowledge server.
Why use it?
They explain how an agent can look up real object names, fields, types and code examples instead of guessing. The instructions also make clear that the agent writes the code itself and only uses the server for reference.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is Zom31C/1confdb-knw's own configuration. It tells Claude Code how to work on 1confdb-knw itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything 1confdb-knw configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Zom31C/1confdb-knw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Zom31C/1confdb-knw/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Zom31C/1confdb-knw

Made for: Claude Code.

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 1confdb-knw CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zom31c/1confdb-knw/claude-md/github.svg)](https://agentmods.dev/instructions/zom31c/1confdb-knw/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/zom31c/1confdb-knw/claude-md"><img src="https://agentmods.dev/badge/instructions/zom31c/1confdb-knw/claude-md/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 1confdb-knw CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zom31c/1confdb-knw/claude-md"><img src="https://agentmods.dev/badge/instructions/zom31c/1confdb-knw/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,464 This file is loaded in full into every session.
When invoked 2,464 The same file — it is already loaded in full.
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 $0.02464 $0.02464
Opus 5 $0.01232 $0.01232
Sonnet 5 $0.00493 $0.00493
Haiku 4.5 $0.00246 $0.00246

Measured 8d ago against content hash 76eda0c6105a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

1confdb-knw 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 8d 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.

CLAUDE.md · 149 lines

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.

CLAUDE.md — написание кода 1С с опорой на базу знаний 1confdb-knw

Этот репозиторий содержит экстрактор конфигураций 1С:Предприятие 8 в SQLite и MCP-сервер 1confdb-knw — read-only базу знаний по конкретной конфигурации: объекты метаданных, реквизиты с типами, табличные части, модули кода (BSL), запросы СКД. Сервер НЕ изменяет конфигурацию — он справочный; код и запросы ты пишешь сам, а из базы берёшь факты: имена объектов, полей, методы-примеры.

Инструкции протокола (initialize.instructions) уже содержат полный справочник по схеме БД и глоссарий; этот файл задаёт рабочий процесс и стиль кода.

Подключение к серверу

  • stdio: 1confdb-knw.bat <база.sqlite> (или python -m confdb.mcp_server <база>);
  • сеть: 1confdb-knw.bat <база> --port 8765, клиент — {"url": "http://127.0.0.1:8765/mcp"}; с другой машины — через туннель ssh -L 8765:127.0.0.1:8765 user@host.

Если сервер не поднят, попроси пользователя запустить его (confdb-ui.bat, пункт 1) или запусти сам одной из команд выше.

Глоссарий 1С

Catalog = справочник, Document = документ, InformationRegister / AccumulationRegister / AccountingRegister = регистры сведений / накопления / бухгалтерии, Enum = перечисление, DataProcessor = обработка, Report = отчёт, DefinedType = определяемый тип, CommonAttribute = общий реквизит, CommonModule = общий модуль. Табличная часть = вложенная «таблица строк» объекта (например, у документа строки с полями). СКД = система компоновки данных (запросы отчётов). Все имена объектов и полей — на русском языке.

Рабочий процесс (инструменты MCP)

  1. find_objects — найти объект по подстроке имени/пути (первый шаг всегда).
  2. object_card — «паспорт»: реквизиты с типами, табличные части с полями, модули, ссылки вперёд/назад. Использовать сразу после поиска.
  3. object_tree — дерево объектов «как в конфигураторе» (формы, команды).
  4. find_field — обратный поиск: у каких объектов есть поле с именем.
  5. refs_of — связи по типам реквизитов (impact analysis: кто ссылается).
  6. module_outline — оглавление модуля: сигнатуры, комментарии, #Если… БЕЗ тел.
  7. find_methodsget_method — найти и ПЕРЕИСПОЛЬЗОВАТЬ существующий код (не изобретай процедуру, если в конфигурации уже есть нужная).
  8. skd_of / find_skd — реальные запросы ЭТОЙ конфигурации к тем же таблицам: лучшие примеры именований и соединений.
  9. check_query — ОБЯЗАТЕЛЬНАЯ проверка каждого твоего запроса перед использованием.
  10. sql — только SELECT, для всего, что не покрыто инструментами выше.

Read the full file on GitHub · 149 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. 8d ago First seen · 149 lines · 2,464 tokens per session scan A 76eda0c6105a

Subscribe to this mod's changes

1confdb-knw CLAUDE.md is an instructions file published in the GitHub repository Zom31C/1confdb-knw (0 stars, last pushed 8d ago), licensed MIT. It adds 2,464 tokens to every session, about $0.0123 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens