agentmods.dev

laws: Skill for Claude Code

.agents/skills/x-run-mcp/SKILL.md

x-run-mcp is a skill for Claude Code, Codex from Totopolis/laws. It costs 56 tokens per session (1,362 once invoked), scanned A, original, BSD-2-Clause.

A setup tool that connects the Russian-law search engine to Claude Code through MCP. MCP is a standard way for an AI client to call external tools during a conversation.

In plain words
What is it for?
Starting, checking, registering, or removing the offline legal-search server for Claude Code.
Why use it?
It lets users search the repository’s legal texts directly in Claude Code instead of running commands manually.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions Codex; $skill-name invocation.

This is Totopolis/laws's own configuration. It tells Claude Code and Codex how to work on laws itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything laws configures →

not rated 0repo changed 24d ago A scan 56 tokens original BSD-2-Clause
View source ↗ Totopolis/laws
Reuse

Borrowing it

Nothing to install: this file belongs to Totopolis/laws. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Totopolis/laws/main/.agents/skills/x-run-mcp/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Totopolis/laws

Made for: Claude Code, Codex.

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 x-run-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/totopolis/laws/x-run-mcp/github.svg)](https://agentmods.dev/skills/totopolis/laws/x-run-mcp)
Your own site
<a href="https://agentmods.dev/skills/totopolis/laws/x-run-mcp"><img src="https://agentmods.dev/badge/skills/totopolis/laws/x-run-mcp/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.

agentmods 80×15 button for x-run-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/totopolis/laws/x-run-mcp"><img src="https://agentmods.dev/badge/skills/totopolis/laws/x-run-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,362 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00056 $0.01362
Opus 5.5 $0.00022 $0.00545
Sonnet 5.5 $0.00011 $0.00272
Haiku 4.5 $0.00006 $0.00136

Measured 24d ago against content hash 93c54cbd42ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

x-run-mcp 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 24d 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/skills/x-run-mcp/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP-сервер поиска по кодексам

Скилл подключает поиск как набор инструментов Codex: после этого искать статьи можно не запуская команд, прямо в разговоре. Тот же самый поиск доступен и без MCP — через $x-search-laws, который зовёт CLI; разница только в способе вызова, движок и данные общие.

Сервер общается по stdio, работает офлайн и считает на процессоре.

Стоит ли подключать

MCP-сервер CLI ($x-search-laws)
первый запрос ~5 с, потом 0,2 с ~6 с каждый вызов
серия запросов быстро: модель остаётся в памяти по 6 с на вызов
память держит ~2,5 ГБ, пока живёт сессия освобождает сразу
настройка нужна регистрация в Codex ничего не нужно

Вывод простой: если поиском будут пользоваться часто и подряд — MCP окупается. Для разовых вопросов достаточно $x-search-laws, и настраивать ничего не надо.

Шаг 1 — убедиться, что система готова

PYTHONPATH=src PYTHONIOENCODING=utf-8 .venv/Scripts/python.exe -m laws_mcp.setup_check

Должно закончиться строкой «система готова». Если нет — сначала $x-prepare-system, подключать нерабочий сервер бессмысленно.

Шаг 2 — проверить сервер вживую, до регистрации

PYTHONPATH=src PYTHONIOENCODING=utf-8 .venv/Scripts/python.exe -m laws_mcp.smoke

Скрипт поднимает сервер подпроцессом и вызывает его инструменты по протоколу — ровно так, как это будет делать Codex. Ожидается список из трёх инструментов и осмысленные результаты поиска. Это надёжнее, чем регистрировать вслепую и разбираться потом.

Шаг 3 — зарегистрировать в Codex

Нужны абсолютные пути: Codex запускает сервер из своего рабочего каталога, а не из папки репозитория.

codex mcp add laws \
  --env PYTHONPATH=<полный путь к репозиторию>/src \
  --env LAWS_ROOT=<полный путь к репозиторию> \
  --env PYTHONIOENCODING=utf-8 \
  -- <полный путь к репозиторию>/.venv/Scripts/python.exe -m laws_mcp.server

На Linux/macOS интерпретатор — .venv/bin/python, PYTHONIOENCODING не нужен.

Read the full file on GitHub · 109 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. 24d ago Changed · +1 lines · -68 tokens per session 93c54cbd42ae
  2. 2mo ago First seen · 108 lines · 124 tokens per session scan A ef769bf121cc

Subscribe to this mod's changes

x-run-mcp is a skill published in the GitHub repository Totopolis/laws (0 stars, last pushed 25d ago), licensed BSD-2-Clause. It adds 56 tokens to every session and 1,362 once invoked, about $0.0002 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 2026-08-31.

Legal and compliancelawsmcp
Related

x-run-mcp compared with skills from other repositories

x-run-mcp next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
x-run-mcpTotopolis/lawsSkill025d agoBSD-2-ClauseA56Claude Code, Codex
contract-reviewerrohasnagpal/legal-ai-skillsSkill20127d agoMITA187Claude Code, Codex
contract-drafterrohasnagpal/legal-ai-skillsSkill20127d agoMITA192Claude Code, Codex
clause-comparatorrohasnagpal/legal-ai-skillsSkill20127d agoMITA146Claude Code, Codex
indemnity-liability-analystrohasnagpal/legal-ai-skillsSkill20127d agoMITA134Claude Code, Codex
investment-and-shareholder-agreement-reviewerrohasnagpal/legal-ai-skillsSkill20127d agoMITA207Claude Code, Codex
legal-opinion-drafterrohasnagpal/legal-ai-skillsSkill20127d agoMITA187Claude Code, Codex