A legal research workflow that grounds business, employment, and contract work in government references and legislation across the US, Canada, and the EU.

Use it to compare legal entities, investigate formation or regulatory requirements, and prepare jurisdiction-specific contract scaffolding.

It helps prevent unsupported legal claims and makes differences between jurisdictions easier to check before drafting.

lex — Skill for Claude Code and Codex by ThomasMoreAI

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.

Any agent

npx skills add ThomasMoreAI/legal-skills-open --skill lex

Clone the repo

git clone --depth 1 https://github.com/ThomasMoreAI/legal-skills-open

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/lex/github.svg)](https://agentmods.dev/skills/thomasmoreai/legal-skills-open/lex)

Your own site

<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/lex"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/lex/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/lex"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/lex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 782 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 92% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00028	$0.00782
Opus 5	$0.00014	$0.00391
Sonnet 5	$0.00006	$0.00156
Haiku 4.5	$0.00003	$0.00078

Measured 9d ago against content hash 6cca59bec293, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

lex 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.

Origin

This is a copy

92% identical to lex-ignvvcio254 — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

cross-jurisdiction/corporate/skills/lex/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LEX: Legal-Entity-X-ref

Overview

LEX is a structured truth engine designed to eliminate legal hallucinations by grounding agents in verified government references and legislation across 29+ jurisdictions. It provides deterministic context for business formation, employment, and contract drafting.

When to Use This Skill

Use when you need to cross-reference or compare legal requirements between different territories, such as verifying the compliance gap between an EU SARL and a US LLC.
Use when working with foundational business or employment documents that require specific, jurisdiction-compliant clauses to be inserted into a professional scaffold.
Use when the user asks about the specific regulatory nuances, formation steps, or "truth-based" definitions of legal entities within the 29 supported jurisdictions (USA, Canada, and the EU).

How It Works

Step 1: Identify Jurisdiction

Before drafting, determine if the user's entity or contract target is in the USA, Canada, or the EU.

Step 2: Search & Fetch Context

Use the CLI shortcuts to find the relevant legal patterns and templates.

Run lex search <query> to find matching templates.
Run lex get <path> to read the granular metadata and requirements.

Step 3: Scaffold Drafting

Generate foundation-level documents using lex draft <description>. This ensures that all drafts include the mandatory AI-generated content disclaimer.

Step 4: Verify Authority

Always include a "Verified Sources" section in your output by running lex verify, which fetches official government links for the retrieved context.

Examples

Example 1: Comparing Employment Laws

# Get the workforce template to compare US vs EU notice periods
lex get templates/02_employment_workforce.md

Example 2: Drafting a Czech Contract

# Create a house sale contract scaffold in Czech language
lex draft "Czech house sale contract"

Best Practices

✅ Trust but Verify: Always include the links provided by lex verify in your output.
✅ Table Formatting: Use tables when comparing results across multiple jurisdictions.
❌ No Guessing: If a jurisdiction is outside the US/EU/CA scope, state that it is outside the LEX "Truth Engine" coverage.
❌ No Anecdotal Advice: Stick strictly to the findings in the templates or verified government domains.

Read the full file on GitHub · 80 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.

9d ago First seen · 80 lines · 28 tokens per session scan A 6cca59bec293

Subscribe to this mod's changes

lex is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (72 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 782 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to lex-ignvvcio254, differing in 11 lines, and is treated as a copy.

Claude Code Legal and compliance Research ai-agents anthropic-skills claude-skills compliance context contract-analysis cross-jurisdictional scaffolding

lex