deskcomm-guias

deskcomm-guias is a cursor rule for Cursor from melgarafael/DeskcommCRM. It costs 444 tokens per session, scanned A, original, MIT.

A routing guide that tells the assistant which DeskcommCRM guide to load for common requests. It covers installation, client setup, metrics, agent prompt problems, contributions, and repository coding rules.

In plain words
What is it for?
Use it to choose the right guide before installing the CRM, configuring a client, analysing results, fixing agent behaviour, contributing code, or changing the repository.
Why use it?
It prevents the agent from missing the specialised instructions that apply to a request. It also points code changes to the project's architecture and contribution rules.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Good fit Use it to choose the right guide before installing the CRM, configuring a client, analysing results, fixing agent behaviour, contributing code, or changing the repository.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/melgarafael/deskcommcrm/deskcomm-guias
About the project

DeskcommCRM is an open-source, self-hosted customer relationship management system for businesses that sell through chat, with AI agents that handle, qualify, and sell through WhatsApp. Businesses use it to manage conversations and sales while keeping the CRM and its data on their own server. The catalogue entries provide agents, instructions, skills, and commands for working with the project.

melgarafael/DeskcommCRM · 4,620 stars · on GitHub · deskcomm.com.br

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/melgarafael/DeskcommCRM

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 deskcomm-guias

README.md
[![agentmods](https://agentmods.dev/badge/rules/melgarafael/deskcommcrm/deskcomm-guias/github.svg)](https://agentmods.dev/rules/melgarafael/deskcommcrm/deskcomm-guias)
Your own site
<a href="https://agentmods.dev/rules/melgarafael/deskcommcrm/deskcomm-guias"><img src="https://agentmods.dev/badge/rules/melgarafael/deskcommcrm/deskcomm-guias/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 deskcomm-guias

Your own site · 80×15
<a href="https://agentmods.dev/rules/melgarafael/deskcommcrm/deskcomm-guias"><img src="https://agentmods.dev/badge/rules/melgarafael/deskcommcrm/deskcomm-guias.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 444 This file is loaded in full into every session.
When invoked 444 The same file — it is already loaded in full.
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 $0.00444 $0.00444
Opus 5.5 $0.00178 $0.00178
Sonnet 5.5 $0.00089 $0.00089
Haiku 4.5 $0.00044 $0.00044

Measured yesterday against content hash 595390b7f1f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

deskcomm-guias 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 yesterday.

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.

.cursor/rules/deskcomm-guias.mdc · 25 lines

What it actually says

Este repositório embute guias (skills em .agents/skills/) para situações recorrentes. Quando o pedido casar, carregue o guia antes de agir — a pessoa pode não saber que ele existe:

  • instalar, subir, atualizar, consertar a instalação numa VPS, domínio, Supabase, WhatsApp que não conecta → deskcomm-instalar
  • usar o CRM no dia a dia, encontrar uma tela, entender um fluxo ou configurar algo pela interface → deskcomm-operacao
  • configurar o CRM para um cliente ou nicho (clínica, imobiliária, serviços, curso, loja, escritório de advocacia): agentes, roteadores, follow-ups, base de conhecimento → deskcomm-cliente-novo
  • revender o CRM como SaaS: painel do dono, planos, teste grátis, cobrar os clientes pela Stripe ou pelo Asaas, régua de atraso, nota fiscal, contrato com o cliente final → deskcomm-saas
  • desempenho, conversão, custo de IA, funil, relatório, "o agente está vendendo?" → deskcomm-metricas
  • o agente responde errado, passa tudo para humano, não usa a agenda, melhorar o prompt → deskcomm-prompt
  • contribuir, corrigir um bug, abrir ou atualizar um PR, migration, conflito com a main → deskcomm-contribuir (rode bash .agents/skills/deskcomm-contribuir/scripts/quem-sou.sh primeiro: se disser mantenedor, este guia fica quieto)
  • criar extensão, plugin, módulo ou tema de nicho; "isto é núcleo ou extensão?" → deskcomm-extensao

Escrevendo código aqui: deskcomm-doutrina (as regras que mais custam) e sistema-vivo (o gate de arquitetura). A doutrina completa é o CLAUDE.md da raiz; o contrato portável é o AGENTS.md.

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. yesterday Changed · +2 lines · +50 tokens per session 595390b7f1f5
  2. 13d ago Changed · +1 lines · +29 tokens per session f9d2df926075
  3. 17d ago Changed · +5 tokens per session cde70a431689
  4. 26d ago Changed · +1 lines · +28 tokens per session 59eeded323c3
  5. 1mo ago First seen · 21 lines · 332 tokens per session scan A 6f077bc92334

Subscribe to this mod's changes

deskcomm-guias is a cursor rule published in the GitHub repository melgarafael/DeskcommCRM (4,620 stars, last pushed today), licensed MIT. It adds 444 tokens to every session, about $0.0018 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 2026-09-12.