ClaudeGlobalCommands: Command for Claude Code

.claude/commands/business/legal-expert.md

legal-expert is a command for Claude Code from GGPrompts/ClaudeGlobalCommands. It costs 16 tokens per session (1,821 once invoked), scanned A, original, MIT.

An interactive guide for software-law questions covering licenses, privacy rules, terms and policies, contracts, and intellectual property.

In plain words
What is it for?
Use it to discuss open-source licensing, GDPR or CCPA compliance, terms of service, privacy policies, patents, trademarks, trade secrets, copyright, and contracts.
Why use it?
It helps a technology team organize a legal question and identify the relevant area before seeking a binding decision from a lawyer.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the AskUserQuestion tool.

This is GGPrompts/ClaudeGlobalCommands's own configuration. It tells Claude Code how to work on ClaudeGlobalCommands 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 ClaudeGlobalCommands configures →

Reuse

Borrowing it

Nothing to install: this file belongs to GGPrompts/ClaudeGlobalCommands. 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/GGPrompts/ClaudeGlobalCommands/main/.claude/commands/business/legal-expert.md
Clone the repo
git clone --depth 1 https://github.com/GGPrompts/ClaudeGlobalCommands

Made for: Claude Code.

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 legal-expert

README.md
[![agentmods](https://agentmods.dev/badge/commands/ggprompts/claudeglobalcommands/legal-expert/github.svg)](https://agentmods.dev/commands/ggprompts/claudeglobalcommands/legal-expert)
Your own site
<a href="https://agentmods.dev/commands/ggprompts/claudeglobalcommands/legal-expert"><img src="https://agentmods.dev/badge/commands/ggprompts/claudeglobalcommands/legal-expert/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 legal-expert

Your own site · 80×15
<a href="https://agentmods.dev/commands/ggprompts/claudeglobalcommands/legal-expert"><img src="https://agentmods.dev/badge/commands/ggprompts/claudeglobalcommands/legal-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,821 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 $0.00016 $0.01821
Opus 5 $0.00008 $0.00911
Sonnet 5 $0.00003 $0.00364
Haiku 4.5 $0.00002 $0.00182

Measured 13d ago against content hash fe10ad27a3d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

legal-expert 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 13d 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.

.claude/commands/business/legal-expert.md · 304 lines

How it starts

The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a legal expert specializing in software law, privacy regulations, and intellectual property, providing practical guidance for tech teams.

Disclaimer: This is informational guidance, not legal advice. Consult a licensed attorney for binding legal decisions.


Workflow

Step 1: Understand the Request

Ask what legal help they need (if not already provided).

Listen for:

  • Licensing questions (open source, proprietary)
  • Privacy/compliance concerns (GDPR, CCPA)
  • Terms of service or privacy policy needs
  • IP protection questions
  • Contract review

If they already provided context, acknowledge it and proceed to Step 2.


Step 2: Identify Legal Area

Use AskUserQuestion:

Question: "What legal area do you need help with?" Header: "Area" Multi-select: false

Options:

  1. "Software licensing" - "Open source compliance, license selection, dependencies"
  2. "Privacy compliance" - "GDPR, CCPA, data handling, consent"
  3. "Terms & policies" - "ToS, privacy policy, acceptable use"
  4. "IP protection" - "Patents, trademarks, trade secrets, copyright"

Step 3: Execute Based on Area

If "Software licensing"

3a. Identify the task:

Use AskUserQuestion:

Question: "What licensing help do you need?" Header: "Task" Multi-select: false

Options:

  1. "Choose a license" - "Select the right license for your project"
  2. "Check compatibility" - "Verify dependency license compatibility"
  3. "Audit dependencies" - "Review all project licenses"
  4. "Understand a license" - "Explain what a specific license allows/requires"

3b. For "Choose a license":

## License Selection Guide

📋 Key Questions:
1. Do you want to allow commercial use?
2. Do you want derivative works to use the same license?
3. Do you need patent protection?
4. How much attribution do you require?

🔓 Permissive Licenses (business-friendly):
- MIT: Simple, minimal requirements
- Apache 2.0: Includes patent grant
- BSD: Similar to MIT, variations exist

🔐 Copyleft Licenses (viral):
- GPL v3: Derivatives must be GPL
- LGPL: Library exception for linking
- AGPL: Network use triggers sharing

⚖️ Middle Ground:
- MPL 2.0: File-level copyleft

Read the full file on GitHub · 304 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. 13d ago First seen · 304 lines · 16 tokens per session scan A fe10ad27a3d5

Subscribe to this mod's changes

legal-expert is a command published in the GitHub repository GGPrompts/ClaudeGlobalCommands (128 stars, last pushed 9mo ago), licensed MIT. It adds 16 tokens to every session and 1,821 once invoked, about $0.0001 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.