agentmods.dev

humanizer-ru AGENTS.md

humanizer-ru AGENTS.md is an instructions file for Codex, OpenCode from Vladimir-Human/humanizer-ru. It costs 1,962 tokens per session, scanned A, original, MIT.

Repository instructions for humanizer-ru, a tool that removes signs of machine-generated writing from Russian text. They document mirrored files, rules that keep continuous integration checks passing, and validation steps.

In plain words
What is it for?
Editing the Russian-text processing skill, updating its markers and examples, keeping mirrored files synchronized, and running repository validation.
Why use it?
They prevent edits from leaving duplicate copies out of sync or violating the checks used before changes are accepted.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

not rated 123 +3 changed today A scan 1,962 tokens original MIT
View the source file Vladimir-Human/humanizer-ru vladimir-human.github.io
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/vladimir-human/humanizer-ru/agents-md
Clone the repo
git clone --depth 1 https://github.com/Vladimir-Human/humanizer-ru

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 humanizer-ru AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vladimir-human/humanizer-ru/agents-md.svg)](https://agentmods.dev/instructions/vladimir-human/humanizer-ru/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/vladimir-human/humanizer-ru/agents-md"><img src="https://agentmods.dev/badge/instructions/vladimir-human/humanizer-ru/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,962 This file is loaded in full into every session.
When invoked 1,962 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 5.1 $0.01962 $0.01962
Opus 5 $0.00981 $0.00981
Sonnet 5 $0.00392 $0.00392
Haiku 4.5 $0.00196 $0.00196

Measured today against content hash 3d26af7c228b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

humanizer-ru 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 today.

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 · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — карта репозитория для агентов-редакторов

Краткая карта для ИИ-агентов, которым дают задачу по правке этого репозитория. Человекам — README.md; здесь только то, что предотвращает частые ошибки агентов.

Что это за репозиторий

humanizer-ru — скилл Agent Skills: находит и снимает следы машинной генерации в русском тексте. Текстовое ядро (SKILL.md + references/) исполняет агент; scripts/, eval/ — валидаторы и корпусы для CI, пользователь их не запускает.

Инварианты (нарушение ломает CI)

  1. Две синхронные копии текстов. SKILL.md и references/*.md существуют в двух местах: корень и dsh/skills/humanizer-ru/. Правишь одну — копируй в другую (гейт check_bundle_sync.py, побайтово, CRLF/LF терпимо). Скрипты scripts/check_markers.py и scripts/scan_soft_signals.py зеркалируются в src/humanizer_ru/ (check_pkg_sync.py).
  2. Переносы строк — LF. Windows-агенты: не оставляй CRLF в текстовых файлах; релизный гейт отвергает CR в архиве.
  3. Новый regex-маркер — полный конвейер: запись в CASES + CLASS_OF (A/B) + три образца (прямой/отрицательный/граничный) + строка в references/chatbot-artifacts-*.md (для паритета) + секция в tests/test-fixtures-cases.md + запись в research/fixtures/marker-sources.json (source_url, accessed, verbatim_sample, fixture в tests/fixtures/) + имя в REGISTERED_CASES (scripts/check_fixture_sources.py) + регенерация markers.v1.json (scripts/export_markers.py) и демо (demo/markers.v1.json + demo/generate_js_rules.py).
  4. Витринные числа — гейты. Счётчики паттернов и гейтов в README RU/EN, CHANGELOG, release-check сверяются машинно (check_docs.py, секция I.17): меняешь число — меняй факт, не только текст.
  5. Гейты умеют падать. Новый валидатор обязан иметь --selftest с негативными кейсами и подключаться в scripts/check_all.py.
  6. Примеры «До/После» не добавляют фактов (check_examples.py): в «После» не появляется чисел, имён, дат, которых не было в «До».
  7. Тексты скилла — без вердиктов об авторстве по мягким признакам (Главное правило SKILL.md): формулировки «вероятно человеческий» и т.п. запрещены; детали — в CHANGELOG 3.11.1/3.12.0.

Read the full file on GitHub · 124 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. today Changed · +9 lines · +167 tokens per session 3d26af7c228b
  2. 6d ago First seen · 115 lines · 1,795 tokens per session scan A 7e8ee696b60c

Subscribe to this mod's changes

humanizer-ru AGENTS.md is an instructions file published in the GitHub repository Vladimir-Human/humanizer-ru (123 stars, last pushed today), licensed MIT. It adds 1,962 tokens to every session, about $0.0098 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.

Writing and docsagent-skillsaiai-detectionhumanizernlprussian
Related

Other instructions, from other repositories

im-not-ai CLAUDE.md

Instructions for epoko77-ai/im-not-ai, covering humanize kr — ai 한글 티 제거 하네스 (v2.3.2), 프로젝트 개요, 철칙, ai 워터마킹에 대한 입장 (2026-08-17 확정) and 디렉토리 구조.

epoko77-ai/im-not-ai · 5,070 tokens

im-not-ai GEMINI.md

Instructions for epoko77-ai/im-not-ai, covering humanize kr — ai 한글 티 제거 (gemini cli extension), 개요, 커스텀 명령, 철칙 (위반 시 즉시 롤백) and do-not (탐지·윤문 모두 제외).

epoko77-ai/im-not-ai · 3,184 tokens

humanizer-zh-tw AGENTS.md

Instructions for nagameTW/humanizer-zh-tw, covering agents.md, 這個 repo 是什麼, 關鍵檔案, 維護契約（改東西前先讀） and 編輯 skill.md.

nagameTW/humanizer-zh-tw · 1,295 tokens

transformers copilot-instructions.md

Copilot instructions for huggingface/transformers, covering copilot-instructions.md guide for hugging face transformers, core project structure, coding conventions for hugging face transformers, copying and inheritance and testing.

huggingface/transformers · 773 tokens

transformers AGENTS.md

AGENTS.md instructions for huggingface/transformers, a project described as: 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

huggingface/transformers · 5 tokens

compromise AGENTS.md

AGENTS.md instructions for spencermountain/compromise, covering agents.md — using compromise, read these first, 30-second mental model, rules that prevent most mistakes and not supported (don't try).

spencermountain/compromise · 1,249 tokens