agentmods.dev

vocero-crm: Instructions file for Codex

AGENTS.md

vocero-crm AGENTS.md is an instructions file for Codex, OpenCode from kevinrivm/vocero-crm. It costs 9,216 tokens per session, scanned A, original, MIT.

Repository instructions for Vocero CRM, a self-hosted customer-management application for WhatsApp conversations, sales stages, and an optional AI agent. They describe its architecture, security rules, and development commands.

In plain words
What is it for?
Use them when developing, reviewing, or running the Vocero CRM codebase and its WhatsApp, database, and AI integrations.
Why use it?
They give coding agents and developers the project rules they must follow, such as keeping organizations separate and protecting WhatsApp and AI credentials. This reduces inconsistent changes and security mistakes.

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 kevinrivm/vocero-crm's own configuration. It tells Codex and OpenCode how to work on vocero-crm 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 vocero-crm configures →

not rated 419repo +22 changed 7d ago A scan 9,216 tokens original MIT
View source ↗ kevinrivm/vocero-crm
Reuse

Borrowing it

Nothing to install: this file belongs to kevinrivm/vocero-crm. 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/kevinrivm/vocero-crm/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/kevinrivm/vocero-crm

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 vocero-crm AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kevinrivm/vocero-crm/agents-md/github.svg)](https://agentmods.dev/instructions/kevinrivm/vocero-crm/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kevinrivm/vocero-crm/agents-md"><img src="https://agentmods.dev/badge/instructions/kevinrivm/vocero-crm/agents-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 vocero-crm AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kevinrivm/vocero-crm/agents-md"><img src="https://agentmods.dev/badge/instructions/kevinrivm/vocero-crm/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9,216 This file is loaded in full into every session.
When invoked 9,216 The same file — it is already loaded in full.
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 $0.09216 $0.09216
Opus 5.5 $0.03686 $0.03686
Sonnet 5.5 $0.01843 $0.01843
Haiku 4.5 $0.00922 $0.00922

Measured 7d ago against content hash 679132af603d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vocero-crm AGENTS.md 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 7d 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.

AGENTS.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Guía de Vocero CRM para agentes y personas

Vocero es un CRM de WhatsApp open source (MIT) y self-hosted: bandeja en tiempo real, pipeline kanban, el perfil y el conocimiento del agente, y un Laboratorio donde clientes simulados lo evalúan antes de hablar con clientes reales. Desde la 2.0 el CRM no trae agente (036): contesta un cerebro conectado al lado (Nea u otro) por el despacho y /api/bot/*. Sin cerebro, es un CRM de bandeja manual. Esta guía sirve igual para Claude Code, Codex, OpenCode o una persona: no depende de skills, scripts ni plugins de ningún asistente.

Principios inviolables

  • Una instancia = un negocio. Self-hosted; aun así, toda tabla de dominio lleva organization_id y toda consulta pasa por scoped().
  • Solo WhatsApp Cloud API oficial. Nada de Baileys ni sesiones web. Todo tráfico a Meta pasa por src/lib/meta/client.ts.
  • Secretos cifrados en reposo (AES-256-GCM, src/lib/crypto/); jamás al cliente ni a logs. Los tokens de WhatsApp y del proveedor de IA solo enseñan sus últimos 4.
  • El token de WhatsApp nunca sale del CRM. Un bot externo conversa a través de /api/bot/*, no con Meta.
  • Soberanía. El núcleo depende solo de Postgres + WhatsApp Cloud API + un proveedor LLM OpenRouter-compatible opcional. Cualquier tercero entra como conector opcional tras bandera, apagado por defecto (docs/adr-001-canales-opcionales.md, docs/adr-002-conectores-de-agenda.md).
  • Español en código, comentarios, UI y documentación.
  • La autoridad máxima es .specify/memory/constitution.md; ante un conflicto, gana la constitución.

Stack

Capa Qué
Framework Next.js 15 (App Router) + React 19, TypeScript estricto (strict + noUncheckedIndexedAccess), alias @/ → src/
BD / ORM PostgreSQL 16 + Drizzle ORM; migraciones SQL versionadas en drizzle/, aplicadas al arrancar el contenedor (scripts/migrate.mjs)
Auth Better Auth + plugin organization (src/lib/auth/); registro público cerrado tras la primera organización
Validación Zod en todo input externo (parseBody en src/lib/api.ts)
Tiempo real SSE en GET /api/events sobre un bus in-process (src/server/events/bus.ts); sin WebSockets ni colas: el trabajo en segundo plano corre dentro del proceso
UI Tailwind CSS con tokens en src/app/globals.css, tema claro/oscuro, white-label por organización
Pruebas Vitest (tests/unit/) + guiones E2E (tests/e2e/*.md) conducidos por scripts/e2e-*.mjs (fetch y, algunos, Playwright) contra la app con mocks
Imagen Docker multi-stage standalone, healthcheck /api/health, publicada en ghcr.io/kevinrivm/vocero-crm:X.Y.Z por .github/workflows/imagen.yml

Read the full file on GitHub · 195 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. 7d ago Changed · +41 tokens per session 679132af603d
  2. 13d ago Changed · +24 tokens per session 0edf0a3ef922
  3. 14d ago Changed · +2 lines · +695 tokens per session e8775ccaa185
  4. 15d ago Changed · +1 lines · +65 tokens per session 4fe45834ab7e
  5. 17d ago Changed · +6 lines · +668 tokens per session 0fafd4d78cac
  6. 22d ago Changed · +1 lines · +154 tokens per session fe6f87c8edfa
  7. 22d ago Changed · +1 lines · +146 tokens per session f8d75b31a877
  8. 23d ago Changed · +3 lines · +746 tokens per session 524778903429
  9. 29d ago First seen · 181 lines · 6,677 tokens per session scan A 0237010b2c98

Subscribe to this mod's changes

vocero-crm AGENTS.md is an instructions file published in the GitHub repository kevinrivm/vocero-crm (419 stars, last pushed 4d ago), licensed MIT. It adds 9,216 tokens to every session, about $0.0369 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 2026-10-09.

Backend and APIsSecurity
Related

vocero-crm AGENTS.md compared with instructions from other repositories

vocero-crm AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
vocero-crm AGENTS.mdkevinrivm/vocero-crmInstructions file4194d agoMITA9,216Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode