bitrix-agent-skill AGENTS.md

bitrix-agent-skill AGENTS.md is an instructions file for Codex, OpenCode from Poliklot/bitrix-agent-skill. It costs 280 tokens per session, scanned A, original, MIT.

A set of project instructions for coding agents working on a Bitrix or 1C-Bitrix project, aimed at a Russian-speaking audience. It specifies the language, tone, terminology, and commit-message format to use.

In plain words
What is it for?
Use it when writing project communication or Git commit messages, especially when Russian is the required working language. It also guides wording for Bitrix-related documentation and explanations.
Why use it?
It keeps agent responses, documentation, release notes, and commits consistent with the project's language and conventions. It also clarifies which technical names and commands should remain unchanged.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/poliklot/bitrix-agent-skill/agents-md
Clone the repo
git clone --depth 1 https://github.com/Poliklot/bitrix-agent-skill

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 bitrix-agent-skill AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/poliklot/bitrix-agent-skill/agents-md.svg)](https://agentmods.dev/instructions/poliklot/bitrix-agent-skill/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/poliklot/bitrix-agent-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/poliklot/bitrix-agent-skill/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 280 This file is loaded in full into every session.
When invoked 280 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00280 $0.00280
Opus 5 $0.00140 $0.00140
Sonnet 5 $0.00056 $0.00056
Haiku 4.5 $0.00028 $0.00028

Measured 3d ago against content hash 4d571a1979e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bitrix-agent-skill 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 3d 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 · 19 lines

What it actually says

Инструкции для агентов

Язык проекта

  • Пиши рабочие ответы, документацию, release notes, описания изменений и пояснения по-русски.
  • Проект ориентирован на русскоязычную аудиторию Bitrix / 1C-Bitrix, поэтому русский язык — основной для коммуникации и справочного слоя.
  • Английский используй только там, где он является частью исходного артефакта: API, namespace, class/function names, команды, stack traces, сообщения инструментов, названия GitHub/Git сущностей, ссылки и точные цитаты внешней документации.
  • Не переводи имена файлов, путей, модулей, классов, методов, параметров компонентов и shell-команды.
  • Если пользователь явно просит другой язык, следуй прямому запросу пользователя.

Тон

  • Формулируй нейтрально и профессионально: “русскоязычная аудитория”, “Bitrix / 1C-Bitrix контекст”, “локальная терминология”.
  • Не используй исключающие или оценочные формулировки про национальность, рынок или пользователей.

Commit messages

  • Для commit message учитывай правила из .agents/rules/commit-messages.md: conventional commit type, затем русское описание уже выполненного изменения.
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. 3d ago First seen · 19 lines · 280 tokens per session scan A 4d571a1979e0

Subscribe to this mod's changes

bitrix-agent-skill AGENTS.md is an instructions file published in the GitHub repository Poliklot/bitrix-agent-skill (22 stars, last pushed 1mo ago), licensed MIT. It adds 280 tokens to every session, about $0.0014 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 2026-08-30.