A project setup guide for the TIA harness, a toolset for working with Siemens TIA Portal projects. It adds the guide to the project's AGENTS.md file, which gives coding agents project instructions.

Use it to initialize or refresh TIA harness instructions in AGENTS.md.

It gives future sessions the correct operating rules for the harness without changing the project's own documentation outside its marked section.

tia.init — Skill for Claude Code and Codex 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 tia.init

Clone the repo

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

Made for: Claude Code, Codex.

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

Your own site

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

Per session 167 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,169 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	$0.00167	$0.01169
Opus 5	$0.00084	$0.00584
Sonnet 5	$0.00033	$0.00234
Haiku 4.5	$0.00017	$0.00117

Measured 10d ago against content hash a1270f01adb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

tia.init 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 10d 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/tia.init/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tia.init — bootstrap the harness guidance into the project AGENTS.md (class R)

Inject (or refresh) the TIA harness operating guide into the current project's ./AGENTS.md, so that future sessions in this repo automatically know how to drive the tia MCP, where the gates/guards are, and the hard-won gotchas. This is class R: deterministic, file-only, never opens TIA Portal and never touches the serve — the only MCP call it may make is the pure, offline tia_guide.

When to use

The user asks to initialize / bootstrap / set up the TIA harness in this project.
The user asks to add or update the harness guidance in AGENTS.md (e.g. after a plugin upgrade ships a newer guide).

Goal

Write the harness guide into ./AGENTS.md (the project at the cwd) inside idempotent markers, so the harness section is self-contained and updatable without disturbing anything the project authored.

Procedure (in order)

Read the guide. Read the harness guide from the first of these that exists — this is the exact content to inject. Do not paraphrase or trim it; inject it verbatim.
1. The tia MCP, if available in this session: call the tia_guide tool with {"topic":"full"} and use the returned markdown. Preferred: always matches the INSTALLED MCP version; pure/offline (needs no serve, opens nothing).
2. ~/.codex/AGENTS.md — where the harness install step puts it (see the harness README). The guide block sits between  markers; inject ONLY the text between the markers.
3. codex/AGENTS.md — only when you are running from a clone of the harness repo itself (same markers rule).
⚠️ Do not read ./AGENTS.md (the target project's own file) as the source — that is the file this skill writes to, and reading it as the guide would re-inject whatever is already there. If neither path above exists: stop and tell the user to install the guide (Copy-Item codex\AGENTS.md $env:USERPROFILE\.codex\AGENTS.md). Do not reconstruct the guide from memory — the gates and gotchas in it are safety-relevant.
Locate / create the target. If ./AGENTS.md does not exist in the current project, create it. If it exists, read it.
Inject between idempotent markers. The guide block is delimited by:

Read the full file on GitHub · 82 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.

10d ago First seen · 82 lines · 167 tokens per session scan A a1270f01adb6

Subscribe to this mod's changes

tia.init is a skill published in the GitHub repository renanlido/tia-harness (5 stars, last pushed 1mo ago), licensed MIT. It adds 167 tokens to every session and 1,169 once invoked, about $0.0008 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

tia.init

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

tia.init — bootstrap the harness guidance into the project AGENTS.md (class R)

When to use

Goal

Procedure (in order)

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