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.
npx skills add sergeionlyart/minius_codex_lab --skill legal-draftinggit clone --depth 1 https://github.com/sergeionlyart/minius_codex_labWrote 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/skills/sergeionlyart/minius_codex_lab/legal-drafting)<a href="https://agentmods.dev/skills/sergeionlyart/minius_codex_lab/legal-drafting"><img src="https://agentmods.dev/badge/skills/sergeionlyart/minius_codex_lab/legal-drafting/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/skills/sergeionlyart/minius_codex_lab/legal-drafting"><img src="https://agentmods.dev/badge/skills/sergeionlyart/minius_codex_lab/legal-drafting.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 | $0.00045 | $0.00929 |
| Opus 5 | $0.00023 | $0.00464 |
| Sonnet 5 | $0.00009 | $0.00186 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
legal-drafting 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 11d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Юридическое drafting
Contract
- Job-to-be-done: подготовить юридический draft из утвержденного evidence ledger без добавления непроверенных тезисов.
- Inputs: адресат, тип документа, язык, scope, evidence ledger, ограничения и критерий готовности.
- Outputs: структурированный draft, claim/evidence links, placeholders, риски и вопросы для утверждения.
- Evidence and safety: не исследуй заново из памяти, не скрывай adverse authority и соблюдай классификацию данных.
- Stop conditions: остановись, если нет минимального evidence gate, владельца финального текста или обязательного шаблона.
- Acceptance test: вручную выбери три существенных тезиса и проследи каждый до evidence unit и точного locator.
Входной gate
До начала должны существовать:
- однозначный вопрос, адресат и дата актуальности;
- утвержденный outline/product type;
- source register;
- evidence ledger для ключевых тезисов;
- перечень adverse/counterevidence;
- список отсутствующих данных и допустимых assumptions;
- язык и ведомственные требования к форме.
Если gate не пройден, создай skeleton с placeholders и верни пробелы coordinator, а не заполняй их памятью модели.
Типы документов
Адаптируй структуру к продукту:
- legal memorandum/opinion;
- служебная/аналитическая записка;
- проект нормативно-правового акта/поправки;
- сравнительная таблица;
- пояснительная записка/обоснование;
- официальный ответ/письмо;
- правовой мониторинговый отчет;
- information request/ТЗ на данные.
Процедура
- Зафиксируй audience и решение, которое документ должен поддержать.
- Создай outline; каждый раздел должен отвечать на вопрос, а не повторять источники.
- Назначь каждому material proposition
claim_idиclaim_type:- fact;
- legal_proposition;
- numeric;
- quotation;
- interpretation;
- assumption;
- recommendation.
- Пиши conclusion-first. После вывода укажи authority/evidence, analysis, contrary position, limitation и consequence.
- Для нормы указывай exact article/part/point и version/as-of.
- Для практики отделяй holding от собственной интерпретации и указывай статус/ограничение выборки.
- Для цифры — period, unit, denominator, source и method.
- Рекомендацию связывай с root cause, actor, instrument, deadline, indicator и risk.
- Неподтвержденное:
- удалить;
- или пометить
[ПОДЛЕЖИТ ПРОВЕРКЕ: ...]; - или явно обозначить как assumption с consequence.
- Выполни consistency pass: terminology, definitions, dates, cross-references, annexes, duplicate claims.
- Для проверяемого результата передай structured spec в
$verifiable-legal-document. - Перед выдачей запусти
$legal-qa-audit.
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.
- 11d ago First seen · 92 lines · 45 tokens per session scan A bd0591aa6cf0
legal-drafting is a skill published in the GitHub repository sergeionlyart/minius_codex_lab (6 stars, last pushed 9d ago), licensed Apache-2.0. It adds 45 tokens to every session and 929 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
legal-citation-comprehensive
A Chinese and foreign legal-citation tool for checking, completing, explaining, and formatting footnotes under the second edition of a legal citation manual. It handles laws, cases, legal documents, and academic sources when the relevant source material is provided.
legal-fact-checker
A Chinese-language fact-checking guide for legal documents such as contracts, case analyses, legal opinions, and legal assignments. It checks provided drafts against factual and legal support without inventing laws, cases, or facts.
legal-research
A Chinese-language legal research workflow for finding laws, regulations, court cases, compensation standards, and legal grounds.
workflow-overview
A workflow guide for handling complex legal matters through assessment, issue identification, source research, reasoning, fact checking, and document output.
tw-legal-rag
A tool for finding real Taiwan court judgments and legal interpretations with verifiable citations before answering questions about Taiwan law.
legal-research
A structured system for legal research involving laws, court decisions, academic sources, arguments, and evidence. It separates facts, legal claims, scholarly views, and the author's own analysis.