practice-lawyer

practice-lawyer is a command for Claude Code from edenbuilds/arya-ai. It costs 53 tokens per session (5,243 once invoked), scanned A, original, MIT.

An interactive mock-court simulator for labour, consumer, civil, writ, criminal, and property cases. It creates a case scenario with a judge, opposing counsel, witnesses, evidence, and a court stage.

In plain words
What is it for?
Rehearsing case arguments, responding to a simulated judge or opposing counsel, questioning witnesses, and practising at different difficulty levels.
Why use it?
It lets lawyers, students, and aspiring litigators practise courtroom decisions and receive performance feedback before handling a real hearing.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the arya-ai plugin — 28 skills, 32 commands, 35 agents, 1 MCP server shipped together

Good fit Rehearsing case arguments, responding to a simulated judge or opposing counsel, questioning witnesses, and practising at different difficulty levels.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/edenbuilds/arya-ai/practice-lawyer
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.

Clone the repo
git clone --depth 1 https://github.com/edenbuilds/arya-ai

Made for: Claude Code.

Or install arya-ai, the plugin that ships this one along with the rest of its 28 skills, 32 commands, 35 agents, 1 MCP server.

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 practice-lawyer

README.md
[![agentmods](https://agentmods.dev/badge/commands/edenbuilds/arya-ai/practice-lawyer/github.svg)](https://agentmods.dev/commands/edenbuilds/arya-ai/practice-lawyer)
Your own site
<a href="https://agentmods.dev/commands/edenbuilds/arya-ai/practice-lawyer"><img src="https://agentmods.dev/badge/commands/edenbuilds/arya-ai/practice-lawyer/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 practice-lawyer

Your own site · 80×15
<a href="https://agentmods.dev/commands/edenbuilds/arya-ai/practice-lawyer"><img src="https://agentmods.dev/badge/commands/edenbuilds/arya-ai/practice-lawyer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,243 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 $0.00053 $0.05243
Opus 5 $0.00026 $0.02622
Sonnet 5 $0.00011 $0.01049
Haiku 4.5 $0.00005 $0.00524

Measured 5d ago against content hash 382526301049, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

practice-lawyer 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 5d 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

Copies of this mod

1 near-identical copy found in the catalogue:

commands/practice-lawyer.md · 607 lines

How it starts

The opening of the file, as written. The whole thing — 607 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Command: Universal Litigation Practice Simulator

Purpose

Interactive mock court practice across ALL legal domains (labour, consumer, civil, writ petitions, criminal) with AI judge, opposing counsel, and witnesses. Provides realistic court simulations, performance feedback, and skill development for lawyers, law students, and aspiring litigators.

Usage

/practice-lawyer [domain] [case-type] [difficulty]

Parameters:

  • domain: labour | consumer | civil | writ | criminal | property
  • case-type: Specific case within domain (e.g., wrongful-termination, rera-complaint, mandamus)
  • difficulty: easy (70% win rate) | medium (50% win rate) | hard (30% win rate)

What This Command Does

1. Generates Realistic Case Scenario

Creates fact pattern with:

  • Background facts (employment details, transaction details, dispute history)
  • Legal issues (what needs to be proven/defended)
  • Evidence available (documents, witnesses)
  • Procedural posture (first hearing, evidence stage, arguments stage)
  • Your role (applicant's counsel OR respondent's counsel)

2. AI Court Simulation

AI Judge: Adapts behavior to court type

  • Labour Court: Patient, worker-friendly, less formal ("Your Honour")
  • Consumer Forum: Semi-formal, pro-consumer bias
  • High Court: Very formal, strict, interventionist ("My Lord")
  • Civil Court: Moderately formal, neutral

AI Opposing Counsel: Domain-appropriate strategies

  • Labour: Employer's lawyer (attacks worker credibility, claims misconduct proven)
  • Consumer: Company's lawyer (claims no deficiency, buyer's contributory negligence)
  • Writ: Government's lawyer (cites alternative remedy, questions locus standi)
  • Civil: Defendant's lawyer (denies breach, claims force majeure)

AI Witnesses: Realistic responses

  • Evasive witnesses ("I don't remember")
  • Hostile witnesses (defensive, argumentative)
  • Cooperative witnesses (answer clearly)
  • Expert witnesses (technical testimony)

3. Interactive Practice Modes

  • Cross-Examination Practice: Question opposing party's witnesses
  • Examination-in-Chief Practice: Elicit testimony from your client
  • Argument Practice: Opening statements, final arguments, rebuttals
  • Objection Handling: Respond to opposing counsel's objections
  • Settlement Negotiation: Practice mediation, conciliation

Read the full file on GitHub · 607 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. 5d ago First seen · 607 lines · 0 tokens per session scan A 382526301049

Subscribe to this mod's changes

practice-lawyer is a command published in the GitHub repository edenbuilds/arya-ai (3 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 5,243 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 2026-09-03.