agentmods.dev

DeskcommCRM: Skill for Codex

.agents/skills/deskcomm-operacao/SKILL.md

deskcomm-operacao is a skill for Codex from melgarafael/DeskcommCRM. It costs 119 tokens per session (1,285 once invoked), scanned A, original, MIT.

A daily-use guide for DeskcommCRM, a customer relationship management system, after it has already been installed.

In plain words
What is it for?
Use it to navigate the interface, follow menu paths, configure existing features, and route installation, customer setup, prompt, or troubleshooting questions to other guides.
Why use it?
It helps users find screens, understand workflows, configure available features, and answer routine questions without changing the code.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is melgarafael/DeskcommCRM's own configuration. It tells Codex how to work on DeskcommCRM itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything DeskcommCRM configures →

not rated 5.2krepo +213 changed 22d ago A scan 119 tokens original MIT
View source ↗ melgarafael/DeskcommCRM deskcomm.com.br
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 · 5,198 stars · on GitHub · deskcomm.com.br

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/melgarafael/DeskcommCRM/main/.agents/skills/deskcomm-operacao/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/melgarafael/DeskcommCRM

Made for: Codex.

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-operacao

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/melgarafael/deskcommcrm/deskcomm-operacao"><img src="https://agentmods.dev/badge/skills/melgarafael/deskcommcrm/deskcomm-operacao.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,285 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 $0.00119 $0.01285
Opus 5.5 $0.00048 $0.00514
Sonnet 5.5 $0.00024 $0.00257
Haiku 4.5 $0.00012 $0.00128

Measured 22d ago against content hash cd0c9e70b7c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

deskcomm-operacao 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 22d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/buscar.sh, scripts/conferir-mapa.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/deskcomm-operacao/SKILL.md · 111 lines

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.

Operar o DeskcommCRM no dia a dia

Este guia é a porta de entrada para dúvidas de uso do produto depois que a instalação já está no ar. Ele evita responder pela memória: localiza a área correta, consulta a documentação atual e encaminha para uma skill especializada quando a pergunta deixar de ser operação cotidiana.

Como agir

  1. Identifique a intenção da pessoa antes de mandar comandos.
  2. Prefira o caminho pela interface quando a tarefa existe na interface.
  3. Diga o caminho como Grupo → Tela → Ação.
  4. Explique o efeito da ação e os pré-requisitos.
  5. Para comportamento que possa ter mudado, confirme em README.md, docs/current-state.md, docs/index.md, no CHANGELOG.md e no código atual.
  6. Não invente campos, botões, estados ou permissões.
  7. Não peça segredo em chat e nunca repita chaves/tokens na resposta.

Quando usar outra skill

  • Instalar, atualizar, VPS, domínio, Supabase, WhatsApp quebrado ou recuperação: deskcomm-instalar.
  • Montar o CRM para um cliente/nicho, configurar agentes, roteadores, follow-ups e conhecimento: deskcomm-cliente-novo.
  • O agente responde errado, escala demais ou não usa ferramentas: deskcomm-prompt.
  • Conversão, desempenho, custo, funil e relatórios: deskcomm-metricas.
  • Alterar/revisar código: deskcomm-doutrina.
  • Abrir contribuição/PR: deskcomm-contribuir.
  • Criar extensão/módulo de nicho: deskcomm-extensao.

Não duplique o procedimento especializado aqui; carregue a skill dona do assunto.

Mapa da interface

Use references/mapa-da-interface.md para orientar perguntas como:

  • "onde vejo conversas?"
  • "onde altero o funil?"
  • "onde configuro IA?"
  • "onde conecto canais?"
  • "onde vejo métricas?"
  • "onde gerencio equipe e organização?"

Como consultar na hora

O mapa acima envelhece; o comando abaixo pergunta ao menu e ao CHANGELOG na hora. Caminhos relativos à pasta desta skill. Use bash scripts/buscar.sh --menu para listar as telas atuais, e bash scripts/buscar.sh <palavra> para achar onde algo mora (ex.: buscar.sh pausar, buscar.sh videochamada, buscar.sh "planos de tarefa"). Pode digitar com ou sem acento: prospecao acha Prospecção. O resultado do comando vale mais que o texto dos arquivos; se discordarem, siga o comando e avise que o arquivo está desatualizado.

Read the full file on GitHub · 111 lines

Files

What ships with it

13 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.

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. 22d ago Changed · +28 lines cd0c9e70b7c2
  2. 1mo ago First seen · 83 lines · 119 tokens per session scan A 60524ce5f7d7

Subscribe to this mod's changes

deskcomm-operacao is a skill published in the GitHub repository melgarafael/DeskcommCRM (5,198 stars, last pushed today), licensed MIT. It adds 119 tokens to every session and 1,285 once invoked, about $0.0005 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 2026-10-03.

E-commerceProductivityRAG and vectorsWriting and docsaicrmlgpdnextjsnuvemshop
Related

deskcomm-operacao compared with skills from other repositories

deskcomm-operacao next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
deskcomm-operacaomelgarafael/DeskcommCRMSkill5.2ktodayMITA119Codex
i18n Completeness Auditlroy-stack/ai-pod-storeSkill111d agononeA59Claude Code
copilotkit-channelsCopilotKit/CopilotKitSkill39ktodayMITA112Claude Code
setup-slack-channelCopilotKit/CopilotKitSkill39ktodayMITA206Claude Code
channels-setupCopilotKit/CopilotKitSkill39ktodayMITA141Claude Code
potpie-source-ingestionpotpie-ai/potpieSkill5.8k7d agoApache-2.0A111Claude Code, Codex
benchmark-workflowxberg-io/xbergSkill9.5ktodayMITA13Claude Code