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.
Borrowing it
Nothing to install: this file belongs to melgarafael/DeskcommCRM. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/melgarafael/DeskcommCRM/main/.agents/skills/deskcomm-instalar/SKILL.mdgit clone --depth 1 https://github.com/melgarafael/DeskcommCRMWrote 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.
[](https://agentmods.dev/skills/melgarafael/deskcommcrm/deskcomm-instalar)<a href="https://agentmods.dev/skills/melgarafael/deskcommcrm/deskcomm-instalar"><img src="https://agentmods.dev/badge/skills/melgarafael/deskcommcrm/deskcomm-instalar/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.
<a href="https://agentmods.dev/skills/melgarafael/deskcommcrm/deskcomm-instalar"><img src="https://agentmods.dev/badge/skills/melgarafael/deskcommcrm/deskcomm-instalar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00173 | $0.03876 |
| Opus 5.5 | $0.00069 | $0.01550 |
| Sonnet 5.5 | $0.00035 | $0.00775 |
| Haiku 4.5 | $0.00017 | $0.00388 |
Grade C, and why
deskcomm-instalar scanned grade C with 2 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 15d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
| **Já tem servidor?** | Sem servidor: o `comecar.sh`, no computador da pessoa, nomeia o plano (2 vCPU / 4 GB, 80 GB, Ubuntu 22.04/24.04, datacenter em São Paulo — o de 1 vCPU / 2 GB **não** dá conta do WhatsApp) e abre Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| **Já tem servidor?** | Sem servidor: o `comecar.sh`, no computador da pessoa, nomeia o plano (2 vCPU / 4 GB, 80 GB, Ubuntu 22.04/24.04, datacenter em São Paulo — o de 1 vCPU / 2 GB **não** dá conta do WhatsApp) e abre How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instalar e operar o DeskcommCRM
Você está conduzindo uma pessoa que, quase sempre, não programa — ou que instala para um cliente e quer acertar de primeira. O produto se vende como "um comando na VPS"; a experiência de instalar é o produto. Seu trabalho é fazer dar certo, não explicar por que deu errado.
Como você fala e age
- Como quem explica para um amigo esperto, não para um engenheiro. "O servidor", "as chaves de acesso", "apontar o endereço do site" — nunca "container", "env var", "A-record" sem traduzir.
- Uma coisa de cada vez. Peça uma informação, espere, siga. Nunca despeje dez perguntas.
- Você faz; a pessoa só entrega o que só ela tem (chaves, senha que ela quer, domínio). Rode os comandos você mesmo. Se estiver num CLI sem terminal, dê um comando por vez, pronto para colar.
- Quando algo falhar, conserte. Leia o erro, diga em uma frase o que houve, resolva. Traga o problema mastigado, não cru.
- Nunca ecoe segredos (chaves, senhas, tokens) de volta no chat, nem os grave em arquivo que
não seja o
.envda instalação.
A fonte da verdade é o instalador, hostgator-setup-kit/install.sh — ele valida cada resposta na
hora (chave da Anthropic testada numa chamada real, connection string testada com uma conexão real).
Quando este guia e o instalador discordarem, o instalador está certo: leia o trecho dele e siga.
Primeiro: descubra o cenário
Quatro perguntas, uma por vez, antes de qualquer comando:
| pergunta | por que importa |
|---|---|
| Onde estamos rodando? — dentro da VPS (por SSH), no computador da pessoa, ou no computador de uma agência que vai instalar na VPS de um cliente | O instalador roda dentro da VPS. Fora dela, você só prepara (domínio, Supabase, chaves) e monta o comando que ela vai colar no servidor |
| Já tem servidor? | Sem servidor: o comecar.sh, no computador da pessoa, nomeia o plano (2 vCPU / 4 GB, 80 GB, Ubuntu 22.04/24.04, datacenter em São Paulo — o de 1 vCPU / 2 GB não dá conta do WhatsApp) e abre o link de parceria. Ele roda de qualquer pasta, sem clone — e este guia pode ter sido aberto fora de um: curl -fsSL https://raw.githubusercontent.com/melgarafael/DeskcommCRM/main/hostgator-setup-kit/comecar.sh | bash (dentro de um clone, bash hostgator-setup-kit/comecar.sh) |
| Onde vai ficar o banco: na nuvem da Supabase ou no próprio servidor? | Decide o instalador e o tamanho do servidor. Régua no passo 3; o modo no próprio servidor (single-server) está em references/supabase-local.md |
| É para você ou para um cliente? | Para cliente, leia references/agencia.md antes de pedir qualquer chave: o token do Supabase é uma chave mestra da conta, e o plano grátis permite 2 projetos por usuário |
What ships with it
8 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.
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.
- 15d ago Changed · +32 lines · +4 tokens per session 36706d485587
- 1mo ago Changed · +1 lines 64192f1ac9fd
- 1mo ago Changed scan A → C d461da940a87
- 1mo ago Changed · +1 lines b3c90faade75
- 1mo ago First seen · 163 lines · 169 tokens per session scan A c1f51280ea91
deskcomm-instalar is a skill published in the GitHub repository melgarafael/DeskcommCRM (5,198 stars, last pushed today), licensed MIT. It adds 173 tokens to every session and 3,876 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-12.
deskcomm-instalar compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| deskcomm-instalarmelgarafael/DeskcommCRM | Skill | 5.2k | today | MIT | C | 173 | Codex |
| vss-setup-behavior-analyticsNVIDIA-AI-Blueprints/video-search-and-summarization | Skill | 2.0k | today | Apache-2.0 | A | 42 | Claude Code, Codex |
| bdd-container-updateNVIDIA-AI-Blueprints/video-search-and-summarization | Skill | 2.0k | today | Apache-2.0 | A | 117 | Cursor |
| compute-env-setupUnicomAI/wanwu | Skill | 2.4k | 14d ago | Apache-2.0 | A | 134 | Claude Code, Codex |
| rag-knowledgevstorm-co/full-stack-ai-agent-template | Skill | 2.0k | 7d ago | MIT | A | 76 | Claude Code |
| vss-setup-video-analytics-apiNVIDIA-AI-Blueprints/video-search-and-summarization | Skill | 2.0k | today | Apache-2.0 | B | 52 | Claude Code, Codex |
| fastgpt-docker-deploylabring/FastGPT | Skill | 30k | yesterday | none | A | 84 | Claude Code, Codex |