openplc-engineering-mcp AGENTS.md

openplc-engineering-mcp AGENTS.md is an instructions file for Codex, OpenCode from industrix-com-br/openplc-engineering-mcp. It costs 271 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for an MCP server used with the OpenPLC Editor, a tool for creating and editing programmable-logic-controller projects. The instructions explain which project behavior and documentation the agent should treat as authoritative.

In plain words
What is it for?
Use them when changing, testing, or documenting the OpenPLC engineering MCP server.
Why use it?
They keep code changes aligned with the current OpenPLC project format and the repository's documented workflow.

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/industrix-com-br/openplc-engineering-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/industrix-com-br/openplc-engineering-mcp

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 openplc-engineering-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/industrix-com-br/openplc-engineering-mcp/agents-md.svg)](https://agentmods.dev/instructions/industrix-com-br/openplc-engineering-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/industrix-com-br/openplc-engineering-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/industrix-com-br/openplc-engineering-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 271 This file is loaded in full into every session.
When invoked 271 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00271 $0.00271
Opus 5 $0.00135 $0.00135
Sonnet 5 $0.00054 $0.00054
Haiku 4.5 $0.00027 $0.00027

Measured 4d ago against content hash 17803bb2b033, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

openplc-engineering-mcp 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 4d 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 · 20 lines

What it actually says

Agent instructions

This repository implements an MCP server for the OpenPLC Editor project. Treat upstream OpenPLC behavior as authoritative when validating project semantics or CLI behavior.

  1. Read docs/index.md first.
  2. Do not preload every document or source file.
  3. Use the task routing table in docs/index.md to load only the relevant context.
  4. Treat implementation and tests as the source of truth when documentation and code disagree.
  5. Update the relevant focused document when behavior, architecture, tooling, or scope changes.
  6. Keep documentation small and link to another document instead of duplicating detailed explanations.

Project principles:

  • OpenPLC project format: support only the current OpenPLC Editor project format. Legacy formats, backward-compatibility fallbacks, migrations, and historical project representations are intentionally out of scope. Do not introduce legacy-format support unless the project scope is explicitly changed;
  • prefer the simplest implementation that solves the current requirement;
  • use the official MCP Python SDK rather than reproducing SDK behavior;
  • expose domain-oriented PLC engineering operations, not generic shell or filesystem access;
  • do not reproduce OpenPLC validation or project semantics when OpenPLC can remain authoritative;
  • add abstractions only when a concrete requirement justifies them.
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. 4d ago First seen · 20 lines · 271 tokens per session scan A 17803bb2b033

Subscribe to this mod's changes

openplc-engineering-mcp AGENTS.md is an instructions file published in the GitHub repository industrix-com-br/openplc-engineering-mcp (0 stars, last pushed today), licensed Apache-2.0. It adds 271 tokens to every session, about $0.0014 per session on Opus 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.