itmcp: Instructions file for Codex

AGENTS.md

itmcp AGENTS.md is an instructions file for Codex, OpenCode from Diversus23/itmcp. It costs 929 tokens per session, scanned A, original, MIT.

A project instruction file for itmcp, a TypeScript and Node.js proxy that connects AI clients to a 1C:Enterprise business system over HTTP.

In plain words
What is it for?
Use it to guide development, testing, building, and committing changes in the itmcp project.
Why use it?
It gives coding agents shared rules about the repository structure, language, commands, comments, tests, and releases.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is Diversus23/itmcp's own configuration. It tells Codex and OpenCode how to work on itmcp 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 itmcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Diversus23/itmcp. 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/Diversus23/itmcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Diversus23/itmcp

Made for: Codex, OpenCode.

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 itmcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/diversus23/itmcp/agents-md/github.svg)](https://agentmods.dev/instructions/diversus23/itmcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/diversus23/itmcp/agents-md"><img src="https://agentmods.dev/badge/instructions/diversus23/itmcp/agents-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 itmcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/diversus23/itmcp/agents-md"><img src="https://agentmods.dev/badge/instructions/diversus23/itmcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 929 This file is loaded in full into every session.
When invoked 929 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 $0.00929 $0.00929
Opus 5.5 $0.00372 $0.00372
Sonnet 5.5 $0.00186 $0.00186
Haiku 4.5 $0.00093 $0.00093

Measured 7d ago against content hash cefb463d9f97, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

itmcp AGENTS.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 7d 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.

AGENTS.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

itmcp

MCP-прокси между AI-клиентами и HTTP-сервисом 1С:Предприятие (решение «Управление IT-отделом 8»). TypeScript, Node, Docker. Общение и комментарии в коде — на русском.

Этот файл — единый источник инструкций для всех AI-агентов (Claude Code, Codex, Cursor и др.). Адаптеры вроде CLAUDE.md только отсылают сюда и не дублируют текст.

Структура

Путь Назначение
src/index.ts, src/main.ts точка входа, CLI (http / stdio)
src/config.ts чтение настроек из переменных окружения
src/http-server.ts Streamable HTTP, OAuth2-эндпоинты, страница входа
src/stdio-server.ts stdio-режим
src/mcp-proxy.ts проксирование Tools / Resources / Prompts в 1С
src/onec-client.ts HTTP-клиент 1С, типизированные ошибки с подсказками
src/auth/ OAuth2, ограничение частоты попыток входа
tests/ vitest; мок 1С поднимается на эфемерном порту
.docs/ документация для сопровождающих

Команды

npm run check   # format:check + lint + typecheck + test — запускать перед коммитом
npm test        # только тесты
npm run build   # tsc в dist/

В lint есть около 30 старых предупреждений no-unsafe-* — они не блокируют. Новый код не должен добавлять ни ошибок, ни предупреждений.

Правила разработки

  • Сначала тест, который падает, потом код. Новые тесты для HTTP-слоя — в tests/http-session.test.ts, для клиента 1С — в tests/onec-client.test.ts.
  • Форматирование — prettier (npx prettier --write), переводы строк LF.
  • Ошибки обращения к 1С — это OneCRequestError (OneCHttpError, OneCConnectionError): message — короткая сводка без внутренних адресов и путей, hint — вероятная причина и что проверить, detail — полные подробности только для лога. Пользователю (MCP-клиенту, странице входа) показывать formatOneCError(e), а не стек и не detail.
  • Отказ в авторизации (401/403) определять по statusCode, а не по тексту сообщения.
  • Секреты (.env, пароли, токены, data/) не коммитить и не выводить в консоль и чат.

Read the full file on GitHub · 52 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. 7d ago First seen · 52 lines · 929 tokens per session scan A cefb463d9f97

Subscribe to this mod's changes

itmcp AGENTS.md is an instructions file published in the GitHub repository Diversus23/itmcp (0 stars, last pushed 2d ago), licensed MIT. It adds 929 tokens to every session, about $0.0037 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 2026-10-30.

Related

itmcp AGENTS.md compared with instructions from other repositories

itmcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
itmcp AGENTS.mdDiversus23/itmcpInstructions file02d agoMITA929Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode