doc-review

doc-review is a skill for Claude Code from Danielmc09/jurisdiction-latam. It costs 76 tokens per session (1,681 once invoked), scanned A, original, Apache-2.0.

A document-auditing skill that checks a complete document against the legal rules loaded for a specific country or region. It reports findings and targeted corrections rather than rewriting the whole document.

In plain words
What is it for?
Use it to review contracts or other regulated documents, classify problems, and identify precise corrections supported by the applicable rules.
Why use it?
It helps find missing requirements, unsupported claims, rules from the wrong jurisdiction, and wording that is too vague. It also stops when required legal information is missing or outdated.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the jurisdiction-kit plugin — 9 skills shipped together

Good fit Use it to review contracts or other regulated documents, classify problems, and identify precise corrections supported by the applicable rules.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/danielmc09/jurisdiction-latam/doc-review
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 Danielmc09/jurisdiction-latam --skill doc-review
Clone the repo
git clone --depth 1 https://github.com/Danielmc09/jurisdiction-latam

Made for: Claude Code.

Or install jurisdiction-kit, the plugin that ships this one along with the rest of its 9 skills.

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 doc-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/danielmc09/jurisdiction-latam/doc-review/github.svg)](https://agentmods.dev/skills/danielmc09/jurisdiction-latam/doc-review)
Your own site
<a href="https://agentmods.dev/skills/danielmc09/jurisdiction-latam/doc-review"><img src="https://agentmods.dev/badge/skills/danielmc09/jurisdiction-latam/doc-review/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 doc-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/danielmc09/jurisdiction-latam/doc-review"><img src="https://agentmods.dev/badge/skills/danielmc09/jurisdiction-latam/doc-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,681 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 $0.00076 $0.01681
Opus 5 $0.00038 $0.00840
Sonnet 5 $0.00015 $0.00336
Haiku 4.5 $0.00008 $0.00168

Measured 11d ago against content hash 48cbae83c03d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

doc-review 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 11d 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.

jurisdiction-kit/skills/doc-review/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Doc Review

Casi ninguna empresa parte de cero. Parte de una plantilla que alguien copió y nadie volvió a mirar.

Frontera con doc-drafter

doc-drafter doc-review
No hay documento. Se genera Ya hay documento. Se audita
De la norma a la cláusula De la cláusula a la norma
Salida: borrador nuevo Salida: hallazgos y correcciones puntuales

Si el documento está tan mal que hay que rehacerlo, este skill lo dice y manda a doc-drafter. No lo reescribe entero por su cuenta.

Requiere

  • El documento completo. No un resumen, no una foto parcial
  • Las capas cargadas de la jurisdicción
  • Verificar el semáforo. Si el pack está VENCIDO, detente

Sin el documento completo, no hay revisión. Opinar sobre cláusulas que no leíste es exactamente lo que hace daño.


Las cinco categorías de hallazgo

Cada hallazgo cae en una y solo una:

# Categoría Qué significa
1 FALTA La norma lo exige y el documento no lo tiene
2 AFIRMA SIN RESPALDO Declara algo que probablemente no es cierto
3 JURISDICCIÓN AJENA Viene de otro país y aquí no aplica
4 VAGO Está, pero tan genérico que no cumple su función
5 NO VERIFICABLE Depende de un hueco declarado del pack

Por qué la 2 va antes que las demás en el reporte

Una omisión es un hueco. Una afirmación falsa es una declaración por escrito.

El caso típico: una política de datos que dice "ciframos toda la información en reposo" cuando no se cifra nada. La omisión se corrige agregando; la afirmación falsa ya está firmada y publicada.

Señales a buscar:

  • Medidas de seguridad declaradas: pregunta cuáles existen de verdad
  • "Cumplimos con la Ley X" — nadie debería afirmar cumplimiento
  • Certificaciones mencionadas: ¿existen y están vigentes?
  • Plazos de respuesta prometidos: ¿hay alguien que los cumpla?
  • Disponibilidad prometida: ¿se mide?

Detector de jurisdicción ajena

El hallazgo más frecuente y el que más rápido se detecta. Un documento copiado de otro país tiene huellas:

Read the full file on GitHub · 182 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. 11d ago First seen · 182 lines · 76 tokens per session scan A 48cbae83c03d

Subscribe to this mod's changes

doc-review is a skill published in the GitHub repository Danielmc09/jurisdiction-latam (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 76 tokens to every session and 1,681 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

software-copyright

A guided workflow for preparing Chinese software copyright registration materials from a real software project. It produces drafts such as application details, source-code documents, and a user manual.

ThomasMoreAI/legal-skills-open · 95 tokens

court-sms

A workflow that reads court text messages or delivery links, extracts case details, downloads court documents, and files them in the matching case folder.

ThomasMoreAI/legal-skills-open · 54 tokens

contract-gen

A legal drafting workflow that collects the key facts and generates a complete contract or agreement in Markdown, with an optional Word version. It can adapt terms to one party’s position within legal limits.

ThomasMoreAI/legal-skills-open · 135 tokens

copyright-docs

Generate software copyright design specification documents compliant with China Copyright Protection Center (CPCC) standards. Creates complete design documents with Mermaid diagrams based on source code analysis. Use for software copyright registration, generating design specification, creating CPCC-compliant…

ThomasMoreAI/legal-skills-open · 87 tokens

terms-generator

Generates comprehensive terms of service by analyzing a website or application to detect business type, data collection, and user interactions. Use when launching a website, app, or SaaS product that needs terms of service with GDPR/CCPA compliance. Trigger with "/terms-generator" or "create terms of service for my…

ThomasMoreAI/legal-skills-open · 69 tokens

wps-contract

A contract document generator for common agreements such as employment, lease, sales, services, software development, and confidentiality contracts. It fills in key details and produces a Word document.

ThomasMoreAI/legal-skills-open · 68 tokens