agentmods.dev

docs_masked AGENTS.md

docs_masked AGENTS.md is an instructions file for Codex, OpenCode from kpshinnik/docs_masked. It costs 612 tokens per session, scanned A, original, MIT.

Repository instructions for a tool that masks personal information in documents and later restores it. They define safety rules, development practices, tests, and how to add detectors or formats.

In plain words
What is it for?
Use them when developing or reviewing the anonymization tool, running its tests and self-check, or extending its supported data formats.
Why use it?
They protect exact restoration, prevent personal documents from entering the repository, and require network requests to pass through the approved safety check.

Instructions file for CodexOpenCode

not rated 15 17d ago A scan 612 tokens original MIT
View the source file kpshinnik/docs_masked
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/kpshinnik/docs_masked/agents-md
Clone the repo
git clone --depth 1 https://github.com/kpshinnik/docs_masked

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 docs_masked AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kpshinnik/docs_masked/agents-md.svg)](https://agentmods.dev/instructions/kpshinnik/docs_masked/agents-md)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 612 This file is loaded in full into every session.
When invoked 612 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 $0.00612 $0.00612
Opus 5 $0.00306 $0.00306
Sonnet 5 $0.00122 $0.00122
Haiku 4.5 $0.00061 $0.00061

Measured 4d ago against content hash 65c0cfbc29a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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 · 46 lines

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

  1. Круговорот точен. unmask(mask(x), mode="sequential") == x для всех поддерживаемых форматов. На каждый формат есть тест.
  2. Единственная точка выхода в сеть — llm.send(), и она обязана вызвать assert_clean() до сетевого запроса. Новые провайдеры добавляются внутрь llm.py, а не мимо него: иначе теряется единственная гарантия, ради которой всё это существует.
  3. Сейф пишется с правами 0600 и никогда не логируется.
  4. Ошибка детекции должна быть безопасной. Лучше замаскировать лишнее, чем пропустить. Слияние двух людей в один тег допустимо, пропуск персональных данных — нет.
  5. Чужие документы не попадают в репозиторий. Каталоги examples/ и private/ в .gitignore. Тесты, которым нужны настоящие договоры, пропускаются, если файлов нет. Всё, что лежит в samples/, 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.

Read the full file on GitHub · 46 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. 4d ago First seen · 46 lines · 612 tokens per session scan A 65c0cfbc29a2

Subscribe to this mod's changes

docs_masked AGENTS.md is an instructions file published in the GitHub repository kpshinnik/docs_masked (15 stars, last pushed 17d ago), licensed MIT. It adds 612 tokens to every session, about $0.0031 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.

LLManonymizationclaudedocxgdprmcp
Related

Other instructions, from other repositories

rizzo-pii CLAUDE.md

Instructions for Rizzo-AI-Academy/rizzo-pii, covering claude.md, cos'è questo progetto, ambiente — vincoli critici e non ovvi, mappa della repo and tassonomia: 22 tag (dettaglio in tassonomiatag.md).

Rizzo-AI-Academy/rizzo-pii · 6,047 tokens

pii-guard AGENTS.md

Instructions for danyuchn/pii-guard, covering agents.md, project overview, tech stack, architecture and commands.

danyuchn/pii-guard · 1,322 tokens

pii-guard CLAUDE.md

Instructions for danyuchn/pii-guard, a project described as: 繁體中文（台灣）個人資料去識別化工具，讓業務文件可以安全地送進 AI 處理 / Reversible Traditional-Chinese (Taiwan) PII de-identification for LLM workflows — fully local.

danyuchn/pii-guard · 3 tokens

piighost CLAUDE.md

Claude Code instructions for Athroniaeth/piighost, covering claude.md, project overview, development commands, architecture and anonymization pipeline.

Athroniaeth/piighost · 2,631 tokens

papyrus AGENTS.md

AGENTS.md instructions for abhichat85/papyrus, covering agents.md, what papyrus is, the one rule, core principles and layout.

abhichat85/papyrus · 1,444 tokens

papyrus CLAUDE.md

Claude Code instructions for abhichat85/papyrus: See AGENTS.md. It is the single source of truth for how to work in this repository — architecture rules, commands, how to add a parser, and the definition of done.

abhichat85/papyrus · 81 tokens