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-cliente-novo/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-cliente-novo)<a href="https://agentmods.dev/skills/melgarafael/deskcommcrm/deskcomm-cliente-novo"><img src="https://agentmods.dev/badge/skills/melgarafael/deskcommcrm/deskcomm-cliente-novo/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-cliente-novo"><img src="https://agentmods.dev/badge/skills/melgarafael/deskcommcrm/deskcomm-cliente-novo.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 | $0.00171 | $0.02007 |
| Opus 5.5 | $0.00068 | $0.00803 |
| Sonnet 5.5 | $0.00034 | $0.00401 |
| Haiku 4.5 | $0.00017 | $0.00201 |
Grade A, and why
deskcomm-cliente-novo 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Montar um cliente novo, por nicho
O onboarding do produto vai até o funil e os convites. O que faz um agente vender de verdade para um nicho — o prompt que conhece o negócio, o roteador quando há mais de um agente, os follow-ups que puxam quem sumiu, a base de conhecimento, a memória da organização, as capacidades certas — fica para depois, e não há tela que conduza isso. Este guia é o passo 8 que o wizard não tem. Um usuário pediu exatamente isto na discussão #673 do repositório.
Como você age
- Triagem antes de qualquer configuração. Você não sabe o negócio da pessoa; ela sabe. Uma
pergunta por vez, do que o sistema exige (
references/triagem.md). - Monta o pacote como texto, depois aplica pela tela. O produto tem portões que só a tela
atravessa (auditoria, publicação com validação, indexação da base). Não crie nada por SQL — o
motor lê a versão publicada do agente, não a tabela; editar direto não muda nada e pula a
auditoria. O caminho por arquivo, para técnicos, está em
references/por-arquivo.md. - Não inventa regra de negócio. Preço, prazo, política de cancelamento, horário: vêm da pessoa ou dos documentos dela. O que não está escrito vira pergunta, não suposição.
- Não repete no prompt o que o motor já impõe. Apresentar-se como assistente, não inventar
preço, respeitar STOP, horário de envio, promessa sem caso aberto — tudo isso é portão mecânico
(
references/prompt-do-agente.md). Prompt que repete gasta contexto e vaza vocabulário. - Publicar é ato humano. Você deixa tudo em rascunho, testa com o botão Testar (que roda o motor real em modo sandbox) e mostra o que o agente responderia; o clique em "Publicar" é da pessoa, ou vem depois de um "pode publicar" explícito.
Passo 0 — onde a pessoa está
Pergunte, uma por vez: a instalação já está no ar e o onboarding terminou (nome do negócio, WhatsApp conectado, atendente básico, funil)? É para o próprio negócio ou para um cliente? Qual o nicho — clínica/consultório, imobiliária, serviços/agência/obra, curso/mentoria/infoproduto, loja, escritório de advocacia?
What ships with it
6 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.
- 1mo ago Changed · +1 lines · +5 tokens per session 24a2f2683fcf
- 1mo ago Changed c7d837f173c8
- 1mo ago First seen · 110 lines · 166 tokens per session scan A 4db61e8b8f4d
deskcomm-cliente-novo is a skill published in the GitHub repository melgarafael/DeskcommCRM (5,198 stars, last pushed today), licensed MIT. It adds 171 tokens to every session and 2,007 once invoked, about $0.0007 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.
deskcomm-cliente-novo compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| deskcomm-cliente-novomelgarafael/DeskcommCRM | Skill | 5.2k | today | MIT | A | 171 | Codex |
| dspyNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 19 | Claude Code, Codex |
| ai-engineering-toolkitsickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 47 | Claude Code |
| llm-app-patternsdavila7/claude-code-templates | Skill | 33k | today | MIT | A | 54 | Claude Code, Codex |
| ai-productsickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 22 | Claude Code |
| llm-opsdavila7/claude-code-templates | Skill | 33k | today | MIT | A | 44 | Claude Code, Codex |
| llm-securityzhaoxuya520/reverse-skill | Skill | 44k | 1mo ago | MIT | A | 37 | Claude Code, Codex |