Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sergeionlyart/minius_codex_labnpx agentmods add skills/sergeionlyart/minius_codex_lab/matter-intakeWrote 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/matter-intake)<a href="https://agentmods.dev/skills/sergeionlyart/minius_codex_lab/matter-intake"><img src="https://agentmods.dev/badge/skills/sergeionlyart/minius_codex_lab/matter-intake/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/matter-intake"><img src="https://agentmods.dev/badge/skills/sergeionlyart/minius_codex_lab/matter-intake.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 | $0.00055 | $0.01021 |
| Opus 5 | $0.00028 | $0.00511 |
| Sonnet 5 | $0.00011 | $0.00204 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade A, and why
matter-intake 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 9d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Matter intake
Contract
- Job-to-be-done: преобразовать поручение в однозначный, классифицированный и проверяемый matter contract.
- Inputs: вопрос, адресат, продукт, юрисдикция, дата актуальности, срок, источники и ограничения.
- Outputs: заполненные MATTER/PLAN, classification, workflow level, unknowns и acceptance criteria.
- Evidence and safety: собирай только необходимые данные, не копируй секреты в публичные запросы и выбирай более строгий класс при сомнении.
- Stop conditions: остановись до исследования, если неясны полномочия, scope, дата, data class или критический conflict.
- Acceptance test: вручную проверь, что другой reviewer может однозначно пересказать вопрос, продукт, deadline и DoD.
Цель
Преобразовать неструктурированный запрос в проверяемое поручение без преждевременных правовых выводов. Результат — созданное дело в matters/<matter-id>/, понятный план, список необходимых источников и явные допущения.
Обязательные входы
Получить из запроса или осторожно реконструировать:
- рабочее название и
matter-id; - заказчика/адресата и назначение результата;
- конкретный юридический или правополитический вопрос;
- юрисдикцию и территориальные/институциональные границы;
- дату актуальности и исследуемый период;
- тип результата, язык, формат, объем и deadline;
- предоставленные файлы/данные и допустимые внешние источники;
- класс данных по
SECURITY.md; - требуемый уровень L0-L3;
- критерий приемки и лицо, принимающее решение.
Не задавай повторно вопрос, если ответ уже есть в материалах. Не делай скрытых предположений.
Процедура
- Классифицируй данные. При неоднозначности выбери более строгий класс. Определи, допустимы ли web search, external repo и субагенты.
- Сформулируй job-to-be-done. Одно предложение: кто должен принять какое решение на основании какого продукта.
- Сформулируй основной вопрос. Он должен допускать проверяемый ответ и дату актуальности.
- Раздели вопросы. Создай issue tree: jurisdiction/competence, applicable law, facts/data, procedure, remedies/risks, implementation/impact — только релевантные ветви.
- Выбери уровень работы:
- L0 — точечный ответ;
- L1 — memorandum/opinion;
- L2 — research dossier;
- L3 — legal monitoring.
- Определи evidence gate. Какой минимум нужен до drafting: например, действующая редакция нормы + 3 ключевых решения + подтвержденные факты.
- Создай дело:
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.
- 9d ago First seen · 88 lines · 55 tokens per session scan A f503f459ec22
matter-intake is a skill published in the GitHub repository sergeionlyart/minius_codex_lab (6 stars, last pushed 7d ago), licensed Apache-2.0. It adds 55 tokens to every session and 1,021 once invoked, about $0.0003 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.