exemplo

exemplo is a cursor rule for Cursor from raphael-florestasm/mcp-glpi. It costs 0 tokens per session (3,392 once invoked), scanned A, original, Apache-2.0.

A sample coding rule showing how an AI agent could connect to GLPI, a help-desk system, through Python code.

In plain words
What is it for?
Use it as a reference when building an agent that logs in to GLPI and works with support data. The excerpt is only an example, not a complete add-on.
Why use it?
It gives a concrete starting example for handling authentication and requests to GLPI instead of designing the connection from nothing.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use it as a reference when building an agent that logs in to GLPI and works with support data. The excerpt is only an example, not a complete add-on.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/raphael-florestasm/mcp-glpi/exemplo
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/raphael-florestasm/mcp-glpi

Made for: Cursor.

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 exemplo

README.md
[![agentmods](https://agentmods.dev/badge/rules/raphael-florestasm/mcp-glpi/exemplo/github.svg)](https://agentmods.dev/rules/raphael-florestasm/mcp-glpi/exemplo)
Your own site
<a href="https://agentmods.dev/rules/raphael-florestasm/mcp-glpi/exemplo"><img src="https://agentmods.dev/badge/rules/raphael-florestasm/mcp-glpi/exemplo/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 exemplo

Your own site · 80×15
<a href="https://agentmods.dev/rules/raphael-florestasm/mcp-glpi/exemplo"><img src="https://agentmods.dev/badge/rules/raphael-florestasm/mcp-glpi/exemplo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 3,392 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.03392
Opus 5.5 $0.00000 $0.01357
Sonnet 5.5 $0.00000 $0.00678
Haiku 4.5 $0.00000 $0.00339

Measured 2mo ago against content hash 47391d5092af, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

exemplo scanned grade A with 1 finding 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

response = requests.get(endpoint, headers=headers)
exemplo.mdc · 477 lines

How it starts

The opening of the file, as written. The whole thing — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Esse é um exemplo de código:

import requests import json

class GLPIClient: def init(self, url, app_token, user_token, entity_id=0): """ Inicializa o cliente GLPI

    Args:
        url: URL base da instância GLPI
        app_token: Token da aplicação
        user_token: Token do usuário
        entity_id: ID da entidade padrão
    """
    self.url = url.rstrip('/')
    self.app_token = app_token
    self.user_token = user_token
    self.session_token = None
    self.entity_id = entity_id
    
def init_session(self):
    """Inicia uma sessão no GLPI e obtém o session-token"""
    endpoint = f"{self.url}/apirest.php/initSession"
    headers = {
        "Content-Type": "application/json",
        "Authorization": f"user_token {self.user_token}",
        "App-Token": self.app_token
    }
    
    response = requests.get(endpoint, headers=headers)
    
    if response.status_code == 200:
        data = response.json()
        self.session_token = data.get('session_token')
        return self.session_token
    else:
        raise Exception(f"Falha ao iniciar sessão: {response.status_code} - {response.text}")

def get_headers(self):
    """Retorna os headers padrão para requisições autenticadas"""
    if not self.session_token:
        raise Exception("Sessão não iniciada. Execute init_session() primeiro")
        
    return {
        "Content-Type": "application/json",
        "Session-Token": self.session_token,
        "App-Token": self.app_token
    }

def search_tickets(self, search_params=None):
    """
    Pesquisa tickets com base nos parâmetros fornecidos
    
    Args:
        search_params: Dicionário com parâmetros de pesquisa
    """
    endpoint = f"{self.url}/apirest.php/Ticket/"
    headers = self.get_headers()
    
    if search_params:
        query_string = "&".join([f"{k}={v}" for k, v in search_params.items()])
        endpoint = f"{endpoint}?{query_string}"
    
    response = requests.get(endpoint, headers=headers)
    
    if response.status_code == 200:
        return response.json()
    else:
        raise Exception(f"Falha ao pesquisar tickets: {response.status_code} - {response.text}")

def get_ticket(self, ticket_id):
    """
    Obtém detalhes de um ticket específico
    
    Args:
        ticket_id: ID do ticket
    """
    endpoint = f"{self.url}/apirest.php/Ticket/{ticket_id}?expand_dropdowns=true&with_logs=true"
    headers = self.get_headers()
    
    response = requests.get(endpoint, headers=headers)
    
    if response.status_code == 200:
        return response.json()
    else:
        raise Exception(f"Falha ao obter ticket: {response.status_code} - {response.text}")

def create_ticket(self, data):
    """
    Cria um novo ticket
    
    Args:
        data: Dicionário com dados do ticket
    """
    endpoint = f"{self.url}/apirest.php/Ticket"
    headers = self.get_headers()
    
    # Adiciona a entidade padrão se não especificada
    if 'entities_id' not in data:
        data['entities_id'] = self.entity_id
    
    response = requests.post(endpoint, headers=headers, json=data)
    
    if response.status_code == 201:
        return response.json()
    else:
        raise Exception(f"Falha ao criar ticket: {response.status_code} - {response.text}")

def update_ticket(self, ticket_id, data):
    """
    Atualiza um ticket existente
    
    Args:
        ticket_id: ID do ticket
        data: Dicionário com dados a serem atualizados
    """
    endpoint = f"{self.url}/apirest.php/Ticket/{ticket_id}"
    headers = self.get_headers()

Read the full file on GitHub · 477 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. 2mo ago First seen · 477 lines · 0 tokens per session scan A 47391d5092af

Subscribe to this mod's changes

exemplo is a cursor rule published in the GitHub repository raphael-florestasm/mcp-glpi (5 stars, last pushed 1y ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,392 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.