Borrowing it
Nothing to install: this file belongs to kpshinnik/docs_masked. 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/kpshinnik/docs_masked/main/AGENTS.mdgit clone --depth 1 https://github.com/kpshinnik/docs_maskedWrote 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/kpshinnik/docs_masked/agents-md)<a href="https://agentmods.dev/instructions/kpshinnik/docs_masked/agents-md"><img src="https://agentmods.dev/badge/instructions/kpshinnik/docs_masked/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/kpshinnik/docs_masked/agents-md"><img src="https://agentmods.dev/badge/instructions/kpshinnik/docs_masked/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 | $0.00612 | $0.00612 |
| Opus 5.5 | $0.00245 | $0.00245 |
| Sonnet 5.5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
docs_masked 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 1mo 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — правила работы в этом репозитории
Здесь живёт сам инструмент обезличивания. Если вы ищете правило, которое нужно
положить в свой проект, оно лежит в templates/AGENTS-rule.md.
Инварианты, которые нельзя ломать
- Круговорот точен.
unmask(mask(x), mode="sequential") == xдля всех поддерживаемых форматов. На каждый формат есть тест. - Единственная точка выхода в сеть —
llm.send(), и она обязана вызватьassert_clean()до сетевого запроса. Новые провайдеры добавляются внутрьllm.py, а не мимо него: иначе теряется единственная гарантия, ради которой всё это существует. - Сейф пишется с правами 0600 и никогда не логируется.
- Ошибка детекции должна быть безопасной. Лучше замаскировать лишнее, чем пропустить. Слияние двух людей в один тег допустимо, пропуск персональных данных — нет.
- Чужие документы не попадают в репозиторий. Каталоги
examples/иprivate/в.gitignore. Тесты, которым нужны настоящие договоры, пропускаются, если файлов нет. Всё, что лежит вsamples/, синтетическое.
Разработка
python3 -m pytest tests/ -q # тесты
python3 -m pii_shield.cli selftest # быстрая проверка круговорота
python3 samples/make_samples.py # пересоздать тестовые документы
python3 _build_html.py # пересобрать README.html
Как добавить детектор
Функция с декоратором @detector(...) в pii_shield/detectors.py плюс тест.
Приоритет решает конфликты перекрытий: 90+ — подтверждённые контрольной суммой
или ключевым словом, 80–89 — устойчивые форматы, 70–79 — эвристики.
Метку нужно добавить в pii_shield/tags.py (LABELS) и, если она должна
работать по умолчанию, в DEFAULT_LABELS в pii_shield/masker.py.
Как добавить формат
Класс-наследник DocumentAdapter в pii_shield/documents.py с read_units()
и write_units(), зарегистрированный в _ADAPTERS. Если формат табличный,
переопределите read_contexts() — заголовок колонки резко повышает точность
на голых числах. Обязателен тест на точный круговорот.
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.
- 1mo ago First seen · 46 lines · 612 tokens per session scan A 65c0cfbc29a2
docs_masked AGENTS.md is an instructions file published in the GitHub repository kpshinnik/docs_masked (21 stars, last pushed 2mo ago), licensed MIT. It adds 612 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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.