lex-vector: Command for Claude Code

.claude/commands/jurisprudence-search.md

jurisprudence-search is a command for Claude Code from PedroGiudice/lex-vector. It costs 0 tokens per session (1,057 once invoked), scanned A, original, MIT.

A command for researching Brazilian court decisions through an automated research agent. It searches official court websites and produces a structured legal report.

In plain words
What is it for?
Use it to investigate a legal topic, find case details such as the case number, judge, and date, and save the findings as a report.
Why use it?
It reduces the need to search several Brazilian court websites manually and helps refine searches when important information is missing.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is PedroGiudice/lex-vector's own configuration. It tells Claude Code how to work on lex-vector 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 lex-vector configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/cmr-auto/claude-work/repos/lex-vector.

Reuse

Borrowing it

Nothing to install: this file belongs to PedroGiudice/lex-vector. 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/PedroGiudice/lex-vector/main/.claude/commands/jurisprudence-search.md
Clone the repo
git clone --depth 1 https://github.com/PedroGiudice/lex-vector

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 jurisprudence-search

README.md
[![agentmods](https://agentmods.dev/badge/commands/pedrogiudice/lex-vector/jurisprudence-search/github.svg)](https://agentmods.dev/commands/pedrogiudice/lex-vector/jurisprudence-search)
Your own site
<a href="https://agentmods.dev/commands/pedrogiudice/lex-vector/jurisprudence-search"><img src="https://agentmods.dev/badge/commands/pedrogiudice/lex-vector/jurisprudence-search/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 jurisprudence-search

Your own site · 80×15
<a href="https://agentmods.dev/commands/pedrogiudice/lex-vector/jurisprudence-search"><img src="https://agentmods.dev/badge/commands/pedrogiudice/lex-vector/jurisprudence-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,057 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 $0.00000 $0.01057
Opus 5 $0.00000 $0.00528
Sonnet 5 $0.00000 $0.00211
Haiku 4.5 $0.00000 $0.00106

Measured 9d ago against content hash d77a4f296b13, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

jurisprudence-search 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.

.claude/commands/jurisprudence-search.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execute the Jurisprudence Research Agent for iterative deep research on Brazilian court jurisprudence.

Usage

/jurisprudence-search "Seu tema de pesquisa juridica"

Or with arguments:

/jurisprudence-search --check   # Check dependencies only
/jurisprudence-search --help    # Show available courts

What This Command Does

  1. Validates that the Gemini ADK environment is properly configured
  2. Executes the Jurisprudence Research Agent with the provided topic
  3. The agent autonomously:
    • Decomposes the legal topic into sub-vectors
    • Executes iterative searches with site restrictions (whitelist of court domains)
    • Extracts jurisprudence metadata (processo, relator, data)
    • Analyzes gaps and refines queries
    • Synthesizes findings into a structured legal report
  4. Saves results to adk-agents/jurisprudence_agent/research_output/

Court Domains (Whitelist)

The agent restricts searches to official Brazilian court domains:

Code Court Domain
STJ Superior Tribunal de Justica stj.jus.br
STF Supremo Tribunal Federal stf.jus.br
TJSP TJ Sao Paulo tjsp.jus.br
TJMG TJ Minas Gerais tjmg.jus.br
TJRJ TJ Rio de Janeiro tjrj.jus.br
TRF1-5 Tribunais Regionais Federais trf1-5.jus.br

Execution

When the user invokes this command, execute:

REPO_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || echo "/home/cmr-auto/claude-work/repos/lex-vector")
cd "$REPO_ROOT/adk-agents/jurisprudence_agent" && source .venv/bin/activate && python agent.py "$ARGUMENTS"

If $ARGUMENTS is empty, ask the user for a legal research topic in Portuguese.

If $ARGUMENTS is --check, run:

REPO_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || echo "/home/cmr-auto/claude-work/repos/lex-vector")
cd "$REPO_ROOT/adk-agents/jurisprudence_agent" && source .venv/bin/activate && python -c "from agent import JurisprudenceAgent; print('OK')"

Read the full file on GitHub · 119 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. 9d ago First seen · 119 lines · 0 tokens per session scan A d77a4f296b13

Subscribe to this mod's changes

jurisprudence-search is a command published in the GitHub repository PedroGiudice/lex-vector (5 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,057 tokens. 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.