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-curso/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-curso)<a href="https://agentmods.dev/skills/melgarafael/deskcommcrm/deskcomm-curso"><img src="https://agentmods.dev/badge/skills/melgarafael/deskcommcrm/deskcomm-curso/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-curso"><img src="https://agentmods.dev/badge/skills/melgarafael/deskcommcrm/deskcomm-curso.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 | $0.00011 | $0.01343 |
| Opus 5.5 | $0.00004 | $0.00537 |
| Sonnet 5.5 | $0.00002 | $0.00269 |
| Haiku 4.5 | $0.00001 | $0.00134 |
Grade A, and why
deskcomm-curso 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 9d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manter o curso atual
Invocação: /deskcomm-curso no Claude Code; $deskcomm-curso no Codex, seguido do pedido.
Esta skill é a automação com IA: você lê as mudanças, corrige o material e executa os capturadores existentes. O planejador só faz a triagem determinística. Não inicie um daemon, agendamento pago nem outra CLI de IA para substituir o trabalho desta sessão.
Localize o clone do melgarafael/DeskcommCRM e leia CLAUDE.md e
docs/runbooks/atualizar-curso.md no clone antes de
operar a bancada. A publicação do site vive em outro repositório,
melgarafael/deskcomm-site. Quando instalada globalmente, resolva esses caminhos a partir
do clone; o diretório global da skill não contém o curso.
Decisões essenciais
- A base é
commit_fontedecurso/publicacao.json, conferida contra o curso que foi efetivamente publicado. Não use “última tag”, data de imagem oupackage.jsoncomo substituto. O recibo exige tambémsite_commitcom SHA completo. Se falta esse vínculo ou uma publicação anterior comprovada, faça rodada completa e diga por quê. - Compare commits exatos. Alteração local ainda não faz parte de
head; registre o estado da fonte que o app usa e recalcule o plano depois de correções e merges. - O plano oferece candidatos, não cobertura exata. Leia o diff inteiro e os arquivos ligados às telas. Mudança compartilhada/API sem mapa pede revisão global. Reduza um recorte só com justificativa pública sustentada pelo código e pela interface observada.
- Aula em espanhol exige a interface real em espanhol, seletores que existem nessa interface e geometria medida de novo. Nunca reutilize a foto ou as caixas de PT como se fossem ES.
- Não abra nem mostre
.env*, chaves oucurso/saida/contas.json. Os programas podem carregar a configuração local gerada. Use somente a bancada descartável, dados fictícios e worker parado; não se conecte ao CRM de um cliente para fotografar ou semear.
What ships with it
2 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.
- 9d ago First seen · 86 lines · 11 tokens per session scan A 70a5df3608f6
deskcomm-curso is a skill published in the GitHub repository melgarafael/DeskcommCRM (5,198 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 1,343 once invoked, about $0.0000 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 2026-10-28.
deskcomm-curso compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| deskcomm-cursomelgarafael/DeskcommCRM | Skill | 5.2k | today | MIT | A | 11 | Codex |
| deeptutor-cliHKUDS/DeepTutor | Skill | 55k | yesterday | Apache-2.0 | A | 42 | Claude Code, Codex |
| retro-learnHoangNguyen0403/agent-skills-standard | Skill | 583 | today | MIT | A | 18 | Codex |
| fastgpt-docker-deploylabring/FastGPT | Skill | 30k | yesterday | none | A | 84 | Claude Code, Codex |
| system-design-case-catalogHoangNguyen0403/agent-skills-standard | Skill | 583 | today | MIT | A | 58 | Claude Code, Codex |
| browser-f8f2966eFuRongJun-1999/dsh-memory | Skill | 604 | today | MIT | A | 72 | Claude Code |
| stripeHybridAIOne/hybridclaw | Skill | 159 | yesterday | MIT | A | 23 | Claude Code |