agentmods.dev

DeskcommCRM: Instructions file for Claude Code

CLAUDE.md

DeskcommCRM CLAUDE.md is an instructions file for Claude Code from melgarafael/DeskcommCRM. It costs 11,834 tokens per session, scanned A, original, MIT.

Project guidance for DeskcommCRM, an open-source sales system with built-in AI agents that supports different business types and uses WhatsApp as its main communication channel.

In plain words
What is it for?
Use it when planning or implementing DeskcommCRM changes, checking documentation, reviewing database or interface work, and validating security and automated tests.
Why use it?
It points agents to the correct source of truth, current project status, documentation order and security model before they change a multi-tenant system, where separate customers share one application safely.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is melgarafael/DeskcommCRM's own configuration. It tells Claude Code 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 844repo +52 changed yesterday A scan 11,834 tokens original MIT
View source ↗ melgarafael/DeskcommCRM 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/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/melgarafael/DeskcommCRM

Made for: Claude Code.

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 DeskcommCRM CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/melgarafael/deskcommcrm/claude-md"><img src="https://agentmods.dev/badge/instructions/melgarafael/deskcommcrm/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11,834 This file is loaded in full into every session.
When invoked 11,834 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.11834 $0.11834
Opus 5 $0.05917 $0.05917
Sonnet 5 $0.02367 $0.02367
Haiku 4.5 $0.01183 $0.01183

Measured yesterday against content hash 27b637fe9fdd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

DeskcommCRM CLAUDE.md scanned grade A with 1 finding 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Conta.** Prova pela tela, dirigindo o browser (Playwright), logando com conta de teste real. `curl`/chamada de API **não** provam UX — validam o backend, mas não o que o usuário vê, clica e entende. Use curl só como
CLAUDE.md · 499 lines

How it starts

The opening of the file, as written. The whole thing — 499 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — DeskcommCRM

Instruções pra futuras sessões Claude trabalhando neste repo. Leitura obrigatória antes de qualquer task de código.

Este arquivo é a doutrina — a autoridade final sobre convenção e anti-pattern. Complementos, na ordem em que ajudam:

  • AGENTS.md — mesmo contrato em forma portável (para Codex/Cursor/Copilot e afins). É derivado deste arquivo, não o substitui. Ao mudar doutrina aqui, verifique se AGENTS.md desatualizou.
  • docs/index.md — índice dos 149 docs, com regra de precedência quando dois docs discordam. Use antes de sair varrendo docs/.
  • docs/current-state.md — o que está pronto, incompleto e quebrado. Leia antes de estimar ou prometer qualquer coisa.
  • docs/harness-audit.md — onde a verificação tem buraco. Importante: pnpm gov:verify não cobre test:db nem test:e2e — verde ali não é prova para mudança de schema ou de UI.
  • docs/threat-model.md — superfície de ataque real do self-host.

Visão (1 parágrafo)

DeskcommCRM é um sistema operacional de vendas open source com agentes de IA nativos — multi-nicho (e-commerce, clínicas, imobiliárias, infoprodutos, serviços), com WhatsApp como canal primário (via WAHA). Agentes com RAG por tenant atendem, qualificam e movem o funil junto com humanos; CRM inteiro exposto via MCP. Monetização = self-host em VPS (parceria HostGator), não assinatura. Arquitetura multi-tenant com RLS desde o dia 1; LGPD nativa. Posicionamento completo: VISION.md.

Stack canônica

  • Frontend: Next.js 16 App Router (Turbopack) + React 19 + TypeScript 6 estrito + Tailwind 4 (config em CSS — ver abaixo) + shadcn/ui (style: new-york, neutral)
  • Backend: Next.js Route Handlers (mesmo repo); workers via event_log table + cron
  • DB: Supabase (Postgres). RLS em toda tabela tenant-aware. Extensions: uuid-ossp, pgcrypto, vector
  • Auth: Supabase Auth via @supabase/ssr. Cookie SameSite=Strict, HttpOnly, Secure
  • Realtime: Supabase Realtime (postgres_changes + broadcast)
  • Storage: Supabase Storage (bucket whatsapp-media privado, URLs assinadas)
  • WhatsApp: WAHA Plus, engine NOWEB
  • Filas/eventos: event_log table + workers (não usar Inngest/Trigger no MVP)
  • Rate limit: Upstash Redis sliding window
  • AI: Vercel AI Gateway (Anthropic primário; OpenAI backup pra embeddings); strings tipo "anthropic/claude-sonnet-4-6"
  • Validação: Zod em todo input externo (request body, webhook payload, env)
  • Observability: Sentry com beforeSend sanitizado

Read the full file on GitHub · 499 lines

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. yesterday Changed · +53 tokens per session 27b637fe9fdd
  2. 4d ago Changed · +8 lines · +339 tokens per session 0e3ecb192062
  3. 5d ago Changed · +2 lines · +41 tokens per session 9c334583e7be
  4. 10d ago First seen · 489 lines · 11,401 tokens per session scan A dee7bc1c34ee

Subscribe to this mod's changes

DeskcommCRM CLAUDE.md is an instructions file published in the GitHub repository melgarafael/DeskcommCRM (844 stars, last pushed yesterday), licensed MIT. It adds 11,834 tokens to every session, about $0.0592 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

E-commerceaicrmlgpdmulti-tenantnextjs
Related

Other instructions, from other repositories

vibetags com-example-service-OrderService.instructions.md

Instructions for PIsberg/vibetags, covering copilot instructions for orderservice, rules for method calculatetax, rules for method processpayment, rules for method validateorder and context & focus.

PIsberg/vibetags · 553 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens