legal-research

legal-research is a skill for Claude Code from joaoguirunas/team-os. It costs 87 tokens per session (2,260 once invoked), scanned A, original, MIT.

A method for legal research based on primary sources such as constitutions, laws, regulations, and court decisions. It sets rules for citing sources, checking whether they are still valid, and separating facts from interpretation.

In plain words
What is it for?
It helps find and cite applicable law, verify amendments and validity, record court decisions, and distinguish source text from legal analysis.
Why use it?
It reduces the risk of relying on outdated, weak, or poorly cited legal information.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit It helps find and cite applicable law, verify amendments and validity, record court decisions, and distinguish source text from legal analysis.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joaoguirunas/team-os/legal-research
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 joaoguirunas/team-os --skill legal-research
Clone the repo
git clone --depth 1 https://github.com/joaoguirunas/team-os

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-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/joaoguirunas/team-os/legal-research/github.svg)](https://agentmods.dev/skills/joaoguirunas/team-os/legal-research)
Your own site
<a href="https://agentmods.dev/skills/joaoguirunas/team-os/legal-research"><img src="https://agentmods.dev/badge/skills/joaoguirunas/team-os/legal-research/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-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/joaoguirunas/team-os/legal-research"><img src="https://agentmods.dev/badge/skills/joaoguirunas/team-os/legal-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,260 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 $0.00087 $0.02260
Opus 5.5 $0.00035 $0.00904
Sonnet 5.5 $0.00017 $0.00452
Haiku 4.5 $0.00009 $0.00226

Measured 20d ago against content hash a307d34556e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

legal-research 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 20d 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/skills/legal-research/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Afirmação jurídica sem fonte é opinião com aparência de lei. Blog resume, resumo distorce, lei muda. Esta skill existe para que tudo o que a squad afirma sobre direito tenha uma fonte primária localizável, com artigo ou número e data — e para que quem lê saiba o que a fonte diz, o que a pesquisadora leu nela e o que ninguém aqui recomenda, porque recomendação é da strategist e parecer é do advogado inscrito da empresa.

1. Princípios

  1. Fonte primária ou nada. Lei com artigo/inciso; acórdão com tribunal, número e data de julgamento; doutrina com autor, obra e ano. Fonte secundária (blog, resumo, notícia, resposta de IA) é pista para achar a primária — nunca entra como fonte.
  2. Toda fonte tem data de consulta e vigência conferida. Lei revogada é histórico, não base. Fonte com mais de 12 meses ou norma alterada desde a consulta → reconsultar e datar de novo.
  3. Achado ≠ leitura ≠ recomendação. Achado é o que a fonte diz. Leitura é interpretação, marcada como tal. Recomendação não existe neste artefato.
  4. Isto não é parecer. Todo research termina com a frase. O advogado inscrito da empresa valida antes de qualquer decisão.
  5. Lacuna declarada vale mais que resposta inventada. O que não foi encontrado sai como [A LEVANTAR: pergunta exata].
  6. Método independente de país. Hierarquia e citação valem em qualquer jurisdição declarada em legal-context.md; onde buscar no Brasil está em reference/fontes-brasil.md.

2. Hierarquia de fontes

Nível Fonte Peso Quando usar
1 Constituição máximo direitos fundamentais, competência, limite a qualquer norma abaixo
2 Lei (complementar, ordinária, código) vinculante regra geral da relação: contrato, dados, trabalho, consumidor
3 Decreto e regulamento vinculante, dentro da lei detalhe operacional: prazos, procedimentos, órgão competente
4 Norma de agência/regulador vinculante no setor obrigações regulatórias, sanções, formulários
5 Jurisprudência (súmula, repetitivo, acórdão) orienta; vincula quando a própria fonte diz como o tribunal aplica a regra; risco em disputa
6 Doutrina argumentativa conceito e interpretação quando a lei é aberta
— Blog, resumo, IA, notícia zero só pista para achar o nível 1–6

Read the full file on GitHub · 114 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 20d ago Changed · -50 tokens per session a307d34556e5
  2. 25d ago First seen · 114 lines · 137 tokens per session scan A 7d9de4041f9d

Subscribe to this mod's changes

legal-research is a skill published in the GitHub repository joaoguirunas/team-os (4 stars, last pushed 2d ago), licensed MIT. It adds 87 tokens to every session and 2,260 once invoked, about $0.0003 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 2026-09-21.

Related

Other skills, from other repositories

bankvertrag-sparkassen-bauvertrag-vob

Für AGB im Bankvertrag Sparkassen und Banken: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: bankvertrag-sparkassen-bauvertrag-vob.

Klotzkette/claude-fuer-deutsches-recht · 68 tokens

kaltstart-triage

Ordnet vorgelegte AGB, Vertragsfassungen und Korrespondenz einem konkreten Prüf-, Entwurfs-, Verhandlungs- oder Streitauftrag zu. Liefert einen belegten Erstbefund und führt nur in die für das Ergebnis benötigten Fachprüfungen.

Klotzkette/claude-fuer-deutsches-recht · 65 tokens

formvorgaben-anzeigen-erklaerungen-309

Für Formvorgaben Anzeigen Erklärungen 309: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.

Klotzkette/claude-fuer-deutsches-recht · 48 tokens

agb-und-cookie-einwilligung-dsgvo

Für AGB und Cookie Einwilligung DSGVO: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.

Klotzkette/claude-fuer-deutsches-recht · 44 tokens

abnahme-testing

Für Abnahme Testing: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.

Klotzkette/claude-fuer-deutsches-recht · 31 tokens

agb-und-ipr-art-6-rom-i-verbraucher

Für AGB und Ipr Art 6 Rom I Verbraucher: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: agb-und-ipr-art-6-rom-i-verbraucher.

Klotzkette/claude-fuer-deutsches-recht · 74 tokens