DeskcommCRM: Instructions file for Codex

AGENTS.md

DeskcommCRM AGENTS.md is an instructions file for Codex, OpenCode from melgarafael/DeskcommCRM. It costs 5,257 tokens per session, scanned A, original, MIT.

Repository instructions for DeskcommCRM, an open-source sales system with built-in AI agents and WhatsApp as its main communication channel. They describe its multi-tenant setup, Brazilian data-protection requirements, technology stack, and key files.

In plain words
What is it for?
Use them to understand the Next.js, Supabase, Redis, AI, WhatsApp, testing, and error-monitoring parts of the project before changing code.
Why use it?
They explain the product rules and deployment risks, including why a change must also work for people installing a fresh copy on their own server.

Instructions file for CodexOpenCode

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

This is melgarafael/DeskcommCRM's own configuration. It tells Codex and OpenCode 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 →

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.md
Clone the repo
git clone --depth 1 https://github.com/melgarafael/DeskcommCRM

Made for: Codex, OpenCode.

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 AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/melgarafael/deskcommcrm/agents-md.svg)](https://agentmods.dev/instructions/melgarafael/deskcommcrm/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/melgarafael/deskcommcrm/agents-md"><img src="https://agentmods.dev/badge/instructions/melgarafael/deskcommcrm/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,257 This file is loaded in full into every session.
When invoked 5,257 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 $0.05257 $0.05257
Opus 5 $0.02629 $0.02629
Sonnet 5 $0.01051 $0.01051
Haiku 4.5 $0.00526 $0.00526

Measured yesterday against content hash dba59c03f85f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

DeskcommCRM AGENTS.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.

4. Tocou UI ou fluxo de usuário → `pnpm test:e2e` com evidência visual. **`curl` não conta**
AGENTS.md · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — DeskcommCRM

Contrato para qualquer agente de código (Codex, Cursor, Copilot, Amp, Claude Code). Este arquivo é o núcleo portável. A doutrina completa e não-negociável vive em CLAUDE.md — leia-o antes de tocar em código. Aqui está o mínimo para não causar dano.


Objetivo do projeto

Sistema operacional de vendas open source com agentes de IA nativos, multi-nicho, WhatsApp como canal primário (via WAHA). Multi-tenant com RLS desde o dia 1, LGPD nativa. Monetização = self-host em VPS, não assinatura. Posicionamento: VISION.md.

Consequência que muda como você trabalha: o produto é distribuído como código. Quem instala numa VPS é o usuário. Uma mudança que funciona na máquina do dev e quebra no clone fresco é um bug de produto, não um detalhe de ambiente.

Stack (CONFIRMADO em package.json)

Next.js 16 (App Router) · React 19 · TypeScript 6 estrito · Tailwind 4 · shadcn/ui · Supabase (Postgres + Auth + Realtime + Storage) · Upstash Redis · Vercel AI Gateway (@ai-sdk/anthropic|openai|google) · WAHA Plus (engine NOWEB) · Zod 4 · Vitest 4 · Playwright 1 · Sentry 10.

Só a major, de propósito: é onde o idioma muda, e é o que tests/unit/agents-md-versoes.test.ts verifica contra o package.json. Declarar a minor aqui fazia todo bump do Dependabot reprovar o verify (5 dos 8 pacotes) e não cobria nada que a major já não cobrisse — issue #235. Para a versão exata, package.json é a fonte.

Runtime: Node ≥22 (.nvmrc = 22; os quatro workflows fixam node-version: 22ci ×2, perf, e2e). Gerenciador: pnpm 9.15.9 (packageManager). Versão do produto: não está escrita aqui, de propósito. Esta linha afirmava 1.0.0 até a v1.6.0 — seis minors de atraso, e nenhum teste a vigiava. Afirmação de versão envelhece a cada release; comando não. A que está publicada agora:

git ls-remote --tags --refs origin 'refs/tags/v*' \
  | sed 's#.*refs/tags/v##' | awk '!/-/' | sort -V | tail -1   # awk, nao grep -v -- '-':
                                                                # em maquina com ugrep aquele nao roda

Read the full file on GitHub · 273 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 · +10 lines · +143 tokens per session dba59c03f85f
  2. 2d ago Changed 1446515c430f
  3. 7d ago First seen · 263 lines · 5,114 tokens per session scan A 91c6adcd652b

Subscribe to this mod's changes

DeskcommCRM AGENTS.md is an instructions file published in the GitHub repository melgarafael/DeskcommCRM (821 stars, last pushed yesterday), licensed MIT. It adds 5,257 tokens to every session, about $0.0263 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.

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

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 · 5,182 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

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

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

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