A rule-based helper that recommends a Siemens S7-1200 or S7-1500 PLC CPU from engineering requirements. An MLFB is Siemens' order number for a specific hardware model, and a TypeIdentifier is the model-and-firmware string TIA Portal uses.

Choose a CPU based on I/O, scan speed, memory, communication ports, safety, redundancy, motion, or PC-based needs.

It gives a concrete starting point when requirements are known but the exact controller is not. The recommendation still needs confirmation against the catalog on the target machine.

cpu.select — Skill for Claude Code by renanlido

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.

Any agent

npx skills add renanlido/tia-harness --skill cpu.select

Clone the repo

git clone --depth 1 https://github.com/renanlido/tia-harness

Made for: Claude Code.

Or install tia-harness, the plugin that ships this one along with the rest of its 8 skills, 4 agents, 1 hook.

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/renanlido/tia-harness/cpu.select/github.svg)](https://agentmods.dev/skills/renanlido/tia-harness/cpu.select)

Your own site

<a href="https://agentmods.dev/skills/renanlido/tia-harness/cpu.select"><img src="https://agentmods.dev/badge/skills/renanlido/tia-harness/cpu.select/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/renanlido/tia-harness/cpu.select"><img src="https://agentmods.dev/badge/skills/renanlido/tia-harness/cpu.select.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 177 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,712 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00177	$0.01712
Opus 5	$0.00088	$0.00856
Sonnet 5	$0.00035	$0.00342
Haiku 4.5	$0.00018	$0.00171

Measured 8d ago against content hash 7cf1adb56642, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cpu.select 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 8d 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.

codex/skills/cpu.select/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cpu.select — heuristic CPU selection (class R, no MCP)

Map an engineering need to a concrete SIMATIC CPU recommendation: family → sub-family/variant → a representative order number (MLFB) → the TIA TypeIdentifier string. Follows the decision logic of the SIMATIC CPU reference (§5) and the §2 hardware guidance of the TIA best-practices baseline (both distilled into CPU-TABLE.md).

This is class R: a deterministic heuristic over the bundled reference table (CPU-TABLE.md). It uses NO MCP tool and does not open TIA. The curated table is a convenience reference, not ground truth — so the recommendation always ends with a flag to resolve the concrete MLFB + firmware against GET /catalog on the target machine before device.create (V21 has no catalog tree-browse; only Find by text/order-number). This gives value early, before the MCP runtime milestones exist.

When to use

The user describes requirements (I/O channels, scan time, memory, PN/DP ports, safety, redundancy, motion, PC-based) and wants a CPU choice.
A project-spec needs a CPU typeIdentifier and the user has criteria, not a model.
Right before spec.validate / scaffold, to fill devices[].typeIdentifier.

Inputs

The need: any of — digital/analog I/O count, scan-time/performance target, program
- data memory size, number/type of fieldbus ports (PROFINET, PROFIBUS DP), safety (SIL/PL), redundancy/availability, motion class (basic positioning vs synchronized/cam/kinematics), PC-based/edge, on-board display, budget/engineering tool.
The bundled reference: CPU-TABLE.md (families, variants, representative MLFBs, the variant-letter decoder, and the decision order).

Outputs

A recommendation containing:

family — S7-1200 or S7-1500 (with the family rationale).
model / subFamily — e.g. CPU 1516-3 PN/DP, sub-family letter (none/C/F/T/R/H/S).
mlfb — a representative order number (e.g. 6ES7 516-3AN02-0AB0).
firmware — a representative /V<major>.<minor> (e.g. /V2.9) — clearly marked as needing catalog confirmation.
typeIdentifier — the assembled OrderNumber:<MLFB>/V<fw> string (slash, never :V).
variant — for S7-1200, the power/output variant (DC/DC/DC vs relay) per the I/O need.
justification — which criteria selected each axis (cite the decision step).
resolveNote — always: "Confirm this MLFB + firmware exists via GET /catalog and pass the returned typeIdentifierNormalized to device.create; do not hand-build the string in production."
capabilityNotes — any gates implied (e.g. relay variant ⇒ no on-board PTO; S7-1200 ⇒ no STL/GRAPH; F-CPU ⇒ safety logic is human-authored/gated, never autonomous).

Read the full file on GitHub · 106 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

CPU-TABLE.md 7.7 KB

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.

8d ago First seen · 106 lines · 177 tokens per session scan A 7cf1adb56642

Subscribe to this mod's changes

cpu.select is a skill published in the GitHub repository renanlido/tia-harness (5 stars, last pushed 1mo ago), licensed MIT. It adds 177 tokens to every session and 1,712 once invoked, about $0.0009 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.

Claude Code Hardware and IoT automation iec-61131-3 industrial-automation mcp openness

cpu.select

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

cpu.select — heuristic CPU selection (class R, no MCP)

When to use

Inputs

Outputs

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

tiaportal-mcp

solidworks-fillet-chamfer-cnc

solidworks-threaded-holes

solidworks-vibecad

eide

workflow