dios-ia-hermes-local: Instructions file for Codex

AGENTS.md

dios-ia-hermes-local AGENTS.md is an instructions file for Codex, OpenCode from fcori47/dios-ia-hermes-local. It costs 3,012 tokens per session, scanned A, original, MIT.

Agent instructions for running Hermes with Ollama locally through Docker. They define the goal, communication style, allowed actions, and which interactive steps belong to the human.

In plain words
What is it for?
Use them when installing or troubleshooting this setup: run permitted Docker commands, configure the local workspace, consult the README for human steps, and guide the user one step at a time in simple Spanish.
Why use it?
They keep setup focused on a local chat, avoid invented commands, and prevent the agent from taking over login, model selection, or interactive chat steps.

Instructions file for CodexOpenCode

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

This is fcori47/dios-ia-hermes-local's own configuration. It tells Codex and OpenCode how to work on dios-ia-hermes-local 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 dios-ia-hermes-local configures →

Reuse

Borrowing it

Nothing to install: this file belongs to fcori47/dios-ia-hermes-local. 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/fcori47/dios-ia-hermes-local/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/fcori47/dios-ia-hermes-local

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 dios-ia-hermes-local AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fcori47/dios-ia-hermes-local/agents-md/github.svg)](https://agentmods.dev/instructions/fcori47/dios-ia-hermes-local/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/fcori47/dios-ia-hermes-local/agents-md"><img src="https://agentmods.dev/badge/instructions/fcori47/dios-ia-hermes-local/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 dios-ia-hermes-local AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/fcori47/dios-ia-hermes-local/agents-md"><img src="https://agentmods.dev/badge/instructions/fcori47/dios-ia-hermes-local/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,012 This file is loaded in full into every session.
When invoked 3,012 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 $0.03012 $0.03012
Opus 5 $0.01506 $0.01506
Sonnet 5 $0.00602 $0.00602
Haiku 4.5 $0.00301 $0.00301

Measured 10d ago against content hash d03e44aad967, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

dios-ia-hermes-local 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 10d 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.

Makes network callslowCapability

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

- **[AGENTE]** El servicio `hermes` corre con `docker compose run --rm` (efímero: se borra al salir), así que **NO** queda contenedor de Hermes en `docker compose ps`. El único persistente es `ollama` (container_name `he
AGENTS.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Guía para agentes de IA

Este archivo es el mapa operativo para un agente de IA (Claude Code, Codex, Cursor o cualquiera) que esté corriendo dentro de la carpeta de este repo. Si un usuario te dice "instalámelo", "guiame" o "ponelo a andar", seguí esto al pie de la letra.

📖 El tutorial humano detallado vive en README.md. Cuando el usuario quiera pasos explicados para leer él, mandalo ahí. Este archivo es para vos, el agente.


🎯 Tu objetivo

Dejar a Hermes + Ollama corriendo 100% local en la máquina del usuario y el chat abierto en su terminal. Nada más. El repo entrega eso: el agente Hermes de Nous Research conectado a un modelo local servido por Ollama, charlando desde la terminal.

Este repo se maneja con comandos docker compose directos (no hay scripts de arranque). Vos podés correr los que NO son interactivos; el login, el selector de modelo y el chat los corre el humano.


🧭 Cómo comportarte

  • Hablá en español simple y directo. Asumí que el usuario puede no ser técnico.
  • Una cosa a la vez. No tires 5 comandos juntos: explicá el paso, esperá, seguí.
  • No inventes comandos. Usá solo lo que existe en este repo: docker compose ... y editar .env. Si dudás, leé el archivo (docker-compose.yml, .env.example) antes de afirmar nada.
  • Sé honesto con los límites. No prometas que "se hace todo solo". Hay cosas que vos NO podés hacer (ver más abajo) y tenés que decirlo claro y pasarle la posta al humano.
  • No alucines features. Este repo NO arma Telegram, WhatsApp, Discord, Slack, mail, crons, memoria ni skills. Eso es del agente Hermes de Nous Research y se activa adentro de Hermes → derivá a nousresearch.com. Este repo solo entrega Hermes + Ollama local + chat en la terminal.
  • Cuando algo falle, leé el error real (pedí que el humano te pegue lo que vio) y diagnosticá. No adivines.

✅ Lo que PODÉS ejecutar vos (agente)

Todo esto es no interactivo y seguro de correr en tu shell:

Read the full file on GitHub · 139 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. 10d ago First seen · 139 lines · 3,012 tokens per session scan A d03e44aad967

Subscribe to this mod's changes

dios-ia-hermes-local AGENTS.md is an instructions file published in the GitHub repository fcori47/dios-ia-hermes-local (11 stars, last pushed 2mo ago), licensed MIT. It adds 3,012 tokens to every session, about $0.0151 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

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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