Saturn AGENTS.md

Integration instructions for Saturn, a local-network service that lets computers discover and use shared AI services without individual API keys or accounts. The services use the same request format as OpenAI’s chat API.

In plain words
What is it for?
Use it to discover AI services on a local network, check their health and available models, and send chat requests, including streamed responses.
Why use it?
It explains how to find a Saturn service and send requests to it from Python, TypeScript, or shell commands.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/jperrello/saturn/agents-md
Clone the repo
git clone --depth 1 https://github.com/jperrello/Saturn

Made for: Codex, OpenCode.

Per session 350 This file is loaded in full into every session.
When invoked 350 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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 $0.00350 $0.00350
Opus 5 $0.00175 $0.00175
Sonnet 5 $0.00070 $0.00070
Haiku 4.5 $0.00035 $0.00035

Measured 2d ago against content hash 5eccc9770dd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Saturn 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 2d 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.

resp = requests.post(f"{best.endpoint}/v1/chat/completions", json={
AGENTS.md · 45 lines

What it actually says

Saturn — Agent Integration Guide

Saturn discovers AI services on the local network via mDNS. No API keys, no configuration, no accounts.

How to use Saturn

Python

from saturn import discover, select_best_service
import requests

services = discover(timeout=5.0)
best = select_best_service(services)
resp = requests.post(f"{best.endpoint}/v1/chat/completions", json={
    "model": "openai/gpt-4o",
    "messages": [{"role": "user", "content": "Hello"}],
})

TypeScript (AI SDK)

npm install ai-sdk-provider-saturn

Shell (no dependencies)

dns-sd -B _saturn._tcp local
dns-sd -L <service_name> _saturn._tcp local
curl -X POST http://<resolved_host>:<port>/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "openai/gpt-4o", "messages": [{"role": "user", "content": "Hello"}]}'

Endpoints

All Saturn services are OpenAI-compatible:

  • GET /v1/health
  • GET /v1/models
  • POST /v1/chat/completions (supports streaming SSE)

Why Saturn exists

AI services gate access behind per-user subscriptions and API keys. Saturn moves access to the network level: one administrator configures a server, every device on the network discovers it automatically via _saturn._tcp.local. mDNS advertisements. End users perform zero configuration steps.

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. 2d ago First seen · 45 lines · 350 tokens per session scan A 5eccc9770dd0

Subscribe to this mod's changes

Saturn AGENTS.md is an instructions file published in the GitHub repository jperrello/Saturn (10 stars, last pushed 3mo ago), licensed MIT. It adds 350 tokens to every session, about $0.0018 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 2026-08-31.