A coding guide for Structured Text, the PLC programming language used by TwinCAT 3 automation projects. It works with TcKit, which edits project files while preserving their links and identifiers.

It is for adding or changing function blocks, methods, properties, variables, enums, configuration types, and cyclic PLC code in TwinCAT 3 projects.

It reduces the risk of breaking TwinCAT project structure when changing declarations, methods, variables, or program logic.

How georgeturneruk/tckit configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to georgeturneruk/tckit. 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/georgeturneruk/tckit/main/.claude/skills/tc-write-st/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/georgeturneruk/tckit

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/georgeturneruk/tckit/tc-write-st/github.svg)](https://agentmods.dev/skills/georgeturneruk/tckit/tc-write-st)

Your own site

<a href="https://agentmods.dev/skills/georgeturneruk/tckit/tc-write-st"><img src="https://agentmods.dev/badge/skills/georgeturneruk/tckit/tc-write-st/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/georgeturneruk/tckit/tc-write-st"><img src="https://agentmods.dev/badge/skills/georgeturneruk/tckit/tc-write-st.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 270 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,071 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	$0.00270	$0.03071
Opus 5.5	$0.00108	$0.01228
Sonnet 5.5	$0.00054	$0.00614
Haiku 4.5	$0.00027	$0.00307

Measured 2mo ago against content hash 60c585c40ca1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tc-write-st 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.

.claude/skills/tc-write-st/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing ST through TcKit

Follow this procedure every time you produce ST that will be written to the project.

Tool selection — read this before calling anything

These TcKit writer tools go through the selected writer backend (the XAE Automation Interface by default on Windows; a deterministic on-disk XML writer elsewhere or when TCKIT_WRITER=xml), which keeps GUIDs and project cross-references consistent. Use them in place of Edit/Write on .TcPOU or .plcproj files.

Request	Tool
Tweak one line in a method / action / property body	`UpdateMethodBodyPatch(pou, method, old, new)`
Tweak one line in the POU's own declaration block (FB-level `VAR`)	`UpdatePouDeclarationPatch(pou, old, new)`
Tweak one line in the POU's own cyclic body (FB / PRG implementation)	`UpdatePouImplementationPatch(pou, old, new)`
Add one variable to a `VAR_INPUT` / `VAR_OUTPUT` / `VAR` etc. scope	`AddVariable(pou, scope, declaration, item?)`
Rewrite a method / action / property body	`UpdateMethodBody(pou, method, code)`
Rewrite the POU's own declaration block	`UpdatePouDeclaration(pou, code)`
Rewrite the POU's own cyclic body (FB / PRG implementation)	`UpdatePouImplementation(pou, code)`
Add a brand-new method to an existing POU	`AddMethod(pou, method_name, code)`
Add a brand-new property to an existing POU (Get, Set, or both)	`AddProperty(pou, name, return_type, getter_code?, setter_code?)`
Add a brand-new POU (FB / function / program / interface)	`AddPou(name, pou_type, code)`
Add a brand-new GVL (`VAR_GLOBAL` declarations)	`AddGvl(name, code)`
Add a brand-new DUT (struct, enum, or union)	`AddDut(name, code, dut_kind="struct"
Create a brand-new PLC project	`CreateProject(name, path)`
Open / re-open a TwinCAT solution in XAE	`OpenProject(solution_path)`
Read the current item body before deciding on a patch anchor	`GetPouItem(pou, item)` (reader)
Read just the FB-level `VAR` block before `AddVariable`	`GetPouDeclaration(pou)` (reader)

Read the full file on GitHub · 87 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.

examples/fb_template.st 1.2 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.

2mo ago First seen · 87 lines · 270 tokens per session scan A 60c585c40ca1

Subscribe to this mod's changes

tc-write-st is a skill published in the GitHub repository georgeturneruk/tckit (11 stars, last pushed 2mo ago), licensed MIT. It adds 270 tokens to every session and 3,071 once invoked, about $0.0011 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.

Hardware and IoT Languages

tc-write-st next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tc-write-stgeorgeturneruk/tckit	Skill	11	2mo ago	MIT	A	270	Claude Code
cardputer-buddyanthropics/claude-plugins-official	Skill	46k	today	Apache-2.0	A	109	Claude Code
holoscan-install-wheelNVIDIA/skills	Skill	3.9k	today	Apache-2.0	A	34	Claude Code, Codex
doca-argpNVIDIA/skills	Skill	3.9k	today	Apache-2.0	A	277	Claude Code, Codex
holoscan-module-lifecycleNVIDIA/skills	Skill	3.9k	today	Apache-2.0	A	47	Claude Code, Codex
lua_package_authoringespressif/esp-claw	Skill	2.4k	6d ago	Apache-2.0	A	38	Claude Code, Codex
zener-languagediodeinc/pcb	Skill	474	today	MIT	A	19	Claude Code, Codex

tckit: Skill for Claude Code