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-doutrina/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-doutrina)<a href="https://agentmods.dev/skills/melgarafael/deskcommcrm/deskcomm-doutrina"><img src="https://agentmods.dev/badge/skills/melgarafael/deskcommcrm/deskcomm-doutrina/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-doutrina"><img src="https://agentmods.dev/badge/skills/melgarafael/deskcommcrm/deskcomm-doutrina.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 | $0.00097 | $0.01058 |
| Opus 5.5 | $0.00039 | $0.00423 |
| Sonnet 5.5 | $0.00019 | $0.00212 |
| Haiku 4.5 | $0.00010 | $0.00106 |
Grade A, and why
deskcomm-doutrina 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeskcommCRM — doutrina de código
A fonte da verdade é o
CLAUDE.mdda raiz, lido doorigin/maine não de um resumo. Esta skill existe para te fazer abri-lo na hora certa e para carregar as três regras que mais custam caro quando esquecidas.
1. Leia antes de escrever
| arquivo | quando |
|---|---|
CLAUDE.md |
sempre, antes de qualquer código — contém a Definition of Done, que muda |
VISION.md |
antes de decidir escopo, ou de dizer não a uma feature |
docs/doctrine/ |
ao mexer em canal, agente, ou peça que se conecte a outra |
ARCHITECTURE.md |
para a visão de uma página |
Não confie em resumo de doutrina — nem neste arquivo. A Definition of Done já foi de 13 para 14
itens; cópia congelada ensina a regra de ontem. Abra o CLAUDE.md.
2. As três que mais custam
Multi-tenancy. Toda tabela tenant-aware leva organization_id uuid not null e RLS com policy
tenant_isolation_<tabela>_all via fn_user_org_ids(). Service role bypassa RLS — handler que o usa
filtra organization_id manualmente, resolvido de fonte confiável (cookie, JWT, segredo de
webhook, token de path), nunca do body. No backend é sempre getUser(), nunca getSession().
Schema sai em tripla. Arquivo em supabase/migrations/, apêndice idempotente no
supabase/baseline.sql, e linha -- manifest: <o quê e por quê> no cabeçalho do .sql (o MANIFEST.md é histórico; não recebe linha nova). O kit self-host aplica só o baseline — o que
não chega lá não chega em quem instalou numa VPS, que é o cliente que paga. Constraint nova exige
corrigir os dados antes, senão o update.sh do clone quebra.
Nenhuma feature nomeia um provider. Provider vive em lib/channels/. pnpm lint:channels é
catraca com lista de dívida: arquivo novo sujo reprova — e arquivo que ficou limpo e não saiu da
lista também reprova.
3. O eixo que não é técnico
A monetização é self-host em VPS, não assinatura: quem instala é o cliente. Então uma mudança pode ser tecnicamente impecável e ainda assim ser recusada — env var nova sem default quebra instalação fresca, dependência de serviço pago obrigatório quebra o modelo, e a pior de todas é a falha-em-verde: a sonda que declara sucesso medindo caminho diferente do que o usuário usa. Num produto que a pessoa instala sozinha, ela não descobre que está quebrado.
What ships with it
1 file 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 14546943b666
- 1mo ago Changed · +6 lines 63357101036a
- 1mo ago Changed ae26a0d4fa3a
- 1mo ago First seen · 61 lines · 97 tokens per session scan A 3173a2de92bc
deskcomm-doutrina is a skill published in the GitHub repository melgarafael/DeskcommCRM (5,198 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 1,058 once invoked, about $0.0004 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-doutrina compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| deskcomm-doutrinamelgarafael/DeskcommCRM | Skill | 5.2k | today | MIT | A | 97 | Codex |
| trigger-convextriggerdotdev/trigger.dev | Skill | 17k | 3d ago | Apache-2.0 | A | 93 | Claude Code, Codex |
| system-design-data-architectureHoangNguyen0403/agent-skills-standard | Skill | 583 | today | MIT | A | 60 | Claude Code, Codex |
| postgres-semantic-searchlaguagu/claude-code-nextjs-skills | Skill | 72 | 4d ago | MIT | A | 84 | Claude Code |
| create-migrationtale-project/tale | Skill | 42 | today | MIT | A | 173 | Claude Code, Codex |
| oracle-mcp-server-helperoracle-devrel/oracle-ai-developer-hub | Skill | 4.5k | yesterday | none | A | 0 | Claude Code, Codex |
| vector-backend-operationsKnuckles-Team/vector-mcp | Skill | 16 | yesterday | MIT | A | 113 | Claude Code, Codex |