GEVINO-Opto-PNP: Instructions file for Codex

AGENTS.md

GEVINO-Opto-PNP AGENTS.md is an instructions file for Codex, OpenCode from geva-elettronica/GEVINO-Opto-PNP. It costs 1,865 tokens per session, scanned A, original, MIT.

A project instruction file for writing Arduino/C++ firmware for the GEVINO Opto PNP, an industrial programmable controller board. It documents the board's inputs, outputs, communication connections, programming setup, and coding rules.

In plain words
What is it for?
Use it when developing firmware for this board, including reading sensors, controlling outputs, and using its serial or other hardware connections.
Why use it?
It helps an agent write code that matches the board's hardware and avoids unsafe or unsuitable control-flow patterns.

Instructions file for CodexOpenCode

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

This is geva-elettronica/GEVINO-Opto-PNP's own configuration. It tells Codex and OpenCode how to work on GEVINO-Opto-PNP 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 GEVINO-Opto-PNP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to geva-elettronica/GEVINO-Opto-PNP. 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/geva-elettronica/GEVINO-Opto-PNP/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/geva-elettronica/GEVINO-Opto-PNP

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 GEVINO-Opto-PNP AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/geva-elettronica/gevino-opto-pnp/agents-md/github.svg)](https://agentmods.dev/instructions/geva-elettronica/gevino-opto-pnp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/geva-elettronica/gevino-opto-pnp/agents-md"><img src="https://agentmods.dev/badge/instructions/geva-elettronica/gevino-opto-pnp/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 GEVINO-Opto-PNP AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/geva-elettronica/gevino-opto-pnp/agents-md"><img src="https://agentmods.dev/badge/instructions/geva-elettronica/gevino-opto-pnp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,865 This file is loaded in full into every session.
When invoked 1,865 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 $0.01865 $0.01865
Opus 5.5 $0.00746 $0.00746
Sonnet 5.5 $0.00373 $0.00373
Haiku 4.5 $0.00186 $0.00186

Measured 2mo ago against content hash 960c59d1f8d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

GEVINO-Opto-PNP 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 2mo 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 · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Programming guide for the GEVINO Opto PNP

This file is written for LLMs and AI coding agents (Claude Code, Cursor, Copilot, etc.) that write firmware for the GEVINO Opto PNP PLC. It is also useful to human developers. If you are generating Arduino/C++ code for this board, follow these rules.

What the board is

GEVINO Opto PNP is an Arduino Zero compatible industrial PLC based on the Microchip SAMD21 (32-bit ARM Cortex-M0+, 48 MHz, 256 KB flash, 32 KB RAM). It has 11 opto-isolated inputs, 4 short-circuit-protected PNP outputs, 2 analog inputs, an RS485 bus, an SD card slot and optional Ethernet / Wi-Fi / Bluetooth / RTC / cellular modules. Program it with the Arduino IDE using the Arduino SAMD core, selecting Arduino Zero (Native USB Port).

The complete pin map and specifications are in README.md and in the single library header src/gevino_opto_pnp_io.h.

Golden rules

  1. Write non-blocking, state-based code. Prefer switch/case state machines. Never block the loop() with delay() in production logic.
  2. Include only one header: #include "gevino_opto_pnp_io.h". It bundles the I/O definitions, the SAMD21 ADC helpers and the Timer class — there are no other library dependencies.
  3. Do not initialise the I/O yourself. gevino_io_setup() already configures every pin, the drive strength, the LEDs, RS485 and the Ethernet reset. Just call it once in setup().
  4. Read inputs and drive outputs with the macros from gevino_opto_pnp_io.h (In1, setOut1, resOut1, …). Do not hard-code raw pin numbers.

Minimal sketch skeleton

#include "gevino_opto_pnp_io.h"

void setup() {
  SerialUSB.begin(115200);   // USB-C debug console
  Serial.begin(115200);      // Bluetooth SPP-C or Wi-Fi ESP8266 module
  Serial1.begin(115200);     // RS485 bus
  gevino_io_setup();         // configures ALL the board I/O
}

void loop() {
  // non-blocking, state-based logic here
}

Read the full file on GitHub · 191 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. 2mo ago First seen · 191 lines · 1,865 tokens per session scan A 960c59d1f8d0

Subscribe to this mod's changes

GEVINO-Opto-PNP AGENTS.md is an instructions file published in the GitHub repository geva-elettronica/GEVINO-Opto-PNP (5 stars, last pushed 2d ago), licensed MIT. It adds 1,865 tokens to every session, about $0.0075 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 2026-08-31.

Related

GEVINO-Opto-PNP AGENTS.md compared with instructions from other repositories

GEVINO-Opto-PNP AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
GEVINO-Opto-PNP AGENTS.mdgeva-elettronica/GEVINO-Opto-PNPInstructions file52d agoMITA1,865Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, 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