A workflow for creating and checking PLCopen XML, a file format used to move PLC programs between compatible engineering tools such as CODESYS. It generates the file from Structured Text and checks its structure, official schema, and contents before import.

Generating PLCopen XML, validating it, fixing the source code when checks fail, and preparing a file for import into the CODESYS development environment.

It reduces the risk of malformed XML or missing variables when moving PLC code into CODESYS. It also provides a final review and an import checklist.

How efranceschetti/festo-codesys-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to efranceschetti/festo-codesys-mcp. 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/efranceschetti/festo-codesys-mcp/main/.claude/skills/plcopen-xml/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/efranceschetti/festo-codesys-mcp

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/efranceschetti/festo-codesys-mcp/plcopen-xml/github.svg)](https://agentmods.dev/skills/efranceschetti/festo-codesys-mcp/plcopen-xml)

Your own site

<a href="https://agentmods.dev/skills/efranceschetti/festo-codesys-mcp/plcopen-xml"><img src="https://agentmods.dev/badge/skills/efranceschetti/festo-codesys-mcp/plcopen-xml/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/efranceschetti/festo-codesys-mcp/plcopen-xml"><img src="https://agentmods.dev/badge/skills/efranceschetti/festo-codesys-mcp/plcopen-xml.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 371 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 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.

Model	Per session	Once invoked
Fable 5.1	$0.00063	$0.00371
Opus 5.5	$0.00025	$0.00148
Sonnet 5.5	$0.00013	$0.00074
Haiku 4.5	$0.00006	$0.00037

Measured 1mo ago against content hash ee9b2ac92885, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

plcopen-xml scanned grade B 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 1mo 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.

Subtle steeringmediumPrompt injection

Instructions that bias recommendations or shape behaviour without the user noticing.

Any failure -> fix sources, regenerate, restart the chain. NEVER tell the user the file is import-ready before all three pass.

.claude/skills/plcopen-xml/SKILL.md · 29 lines

What it actually says

PLCopen XML Pipeline

PLCopen XML is the #1 hallucination risk in this project. Never hand-write it; never trust it unvalidated.

1. Ground truth first

plc_knowledge action=topic ground-truth (anti-hallucination rules), then xml-rules.
Skip only if already loaded this session.

2. Generate — never hand-write

generate_plcopen_xml with the .st source directory. Fix the .st sources and regenerate rather than editing XML by hand.

3. Validation chain (all three, in order)

validate_plcopen_xml — fast 13-rule sanity gate.
validate_plcopen_xsd — official TC6 v2.00 schema (needs python venv with lxml).
validate_plcopen_semantic — confirms no variables/initializers silently dropped vs the .st sources.

Any failure -> fix sources, regenerate, restart the chain. NEVER tell the user the file is import-ready before all three pass.

4. Delegate the final check

Before the user imports into the CODESYS IDE, delegate to the xml-validator subagent (fast, cheap) for the copy-pasteable verdict report.

5. Import checklist for the user

CODESYS -> File -> Import PLCopen XML -> resolve namespace conflicts -> Build -> Generate Code (expect 0 errors).

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.

1mo ago First seen · 29 lines · 63 tokens per session scan B ee9b2ac92885

Subscribe to this mod's changes

plcopen-xml is a skill published in the GitHub repository efranceschetti/festo-codesys-mcp (2 stars, last pushed 21d ago), licensed MIT. It adds 63 tokens to every session and 371 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Hardware and IoT automation codesys cpx ethercat festo iec-61131-3

codesys

Develop CODESYS Structured Text and Python ScriptEngine workflows; troubleshoot fieldbus and OPC UA integration in a test environment.

alivirgo/Major-AI-Skills · 27 tokens

tia-review

Audit an EXISTING / open TIA project against the engineering baseline (optimized access, symbolic addressing, FB + instance-DB, UDT typing, per-task language, versioned library TYPEs, PLCopen naming) and the verification-ladder posture. USE when the user asks to "review / audit / lint my TIA project", check…

renanlido/tia-harness · 190 tokens

tia-verify

Run the offline VERIFICATION LADDER on an open TIA project (rung 1 compile, only Error blocks; rung 2 consistency + export/COMPARE roundtrip + VCI workspace diff; rung 3 simulation, future) and generate the FAT/SAT I/O list (rung 6, read-only). USE WHEN the user asks to "verify / compile / check the project builds"…

renanlido/tia-harness · 242 tokens

tia-handoff

Prepare a human-approval envelope for a GATED operation — download / CPU-STOP (G3), go-online (G4), network scan (G7), credentials (G6: master secret, UMAC, upload / block / certificate passwords, password policy), safety/F (G5). USE WHEN the user wants to "download / deploy / go online / commission", or after…

renanlido/tia-harness · 189 tokens

spec-plan

Turn a VALIDATED TIA project-spec into the ordered, named sequence of offline build operations WITHOUT mutating anything (a dry plan). USE after spec-validate passes and before tia-scaffold — when the user asks to "plan / preview / dry-run the build", or wants to see exactly what scaffolding a spec would do and in…

renanlido/tia-harness · 186 tokens

spec-validate

Validate a TIA project-spec against the JSON Schema AND the deterministic cross-field engineering rules (same-subnet, unique names, OrderNumber:{MLFB}/V{fw} format, module limits, language-by-family, and the G5 safety rule). USE when the user provides or edits a project-spec, asks to "validate / check / lint my spec"…

renanlido/tia-harness · 172 tokens

festo-codesys-mcp: Skill for Claude Code