Borrowing it
Nothing to install: this file belongs to Vladimir-Human/humanizer-ru. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Vladimir-Human/humanizer-ru/main/AGENTS.mdgit clone --depth 1 https://github.com/Vladimir-Human/humanizer-ruWrote 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/vladimir-human/humanizer-ru/agents-md)<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/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.
<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="Reviewed on agentmods" width="80" 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 5.1 | $0.00606 | $0.00606 |
| Opus 5.5 | $0.00242 | $0.00242 |
| Sonnet 5.5 | $0.00121 | $0.00121 |
| Haiku 4.5 | $0.00061 | $0.00061 |
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 2d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — для агентов, которые правят этот репозиторий
humanizer-ru — навык (Agent Skill), который переписывает русский ИИ-текст по-человечески
и сверяет факты. Всё, что получает пользователь, лежит в skills/humanizer-ru/.
Карта
| Путь | Что это |
|---|---|
skills/humanizer-ru/SKILL.md |
инструкция для агента, главный файл продукта |
skills/humanizer-ru/references/ |
примеры «было → стало» и границы признаков |
skills/humanizer-ru/scripts/ |
check_facts.py, clean_paste.py: только стандартная библиотека Python |
eval/ |
слепое сравнение с другими навыками на русских ИИ-текстах |
scripts/ |
проверка репозитория, проверка скриптов навыка на текстах замеров, сборка архива для Claude.ai |
tests/ |
тесты скриптов и проверки репозитория |
.grace/ |
требования, граф модулей и карта проверок (GRACE) |
Правила
- Меняешь поведение навыка — прогони сравнение (
eval/README.md) хотя бы на dev-наборе и сравни с прошлым итогом. Правка, которая ухудшает итог, не принимается. - SKILL.md держи коротким: новое правило заменяет старое, а не добавляется сверху.
Примеры — в
references/. - Скрипты навыка без внешних зависимостей. Новый случай — тест в
tests/. - Версия меняется одновременно в SKILL.md,
.claude-plugin/*.json,.codex-plugin/plugin.jsonи CHANGELOG;python scripts/check_repo.pyэто проверяет. - Переводы строк LF, без невидимых символов в файлах навыка.
- Не запускать локальные нейросетевые модели (решение владельца).
- Меняешь поведение скрипта — обнови контракт в коде и
.grace/.
Перед коммитом:
python scripts/check_repo.py
python -m unittest discover -s tests
Меняешь скрипт навыка — ещё python scripts/check_scripts.py --against main: свойства на всех
текстах eval/ должны выполняться, а каждую новую ошибку сверки прочитай глазами (ложная
тревога на старых правках — дефект скрипта, а не правки).
Версия 3 (исследования, гейты, пакет PyPI, MCP) — в ветке legacy-v3, в main её не возвращать.
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.
- 2d ago Changed · +4 lines · +83 tokens per session 257a0790713c
- 12d ago Changed · -93 lines · -1,571 tokens per session fd733e411a40
- 1mo ago Changed 72281ce2916d
- 1mo ago Changed · -19 tokens per session ea3b3f86befb
- 1mo ago Changed · +5 lines · +84 tokens per session d91dc0bd0cd2
- 1mo ago Changed · +3 lines · +67 tokens per session 6df75ff1199f
- 1mo ago Changed · +9 lines · +167 tokens per session 3d26af7c228b
- 1mo ago First seen · 115 lines · 1,795 tokens per session scan A 7e8ee696b60c
humanizer-ru AGENTS.md is an instructions file published in the GitHub repository Vladimir-Human/humanizer-ru (134 stars, last pushed 2d ago), licensed MIT. It adds 606 tokens to every session, about $0.0024 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 2026-08-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.