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.
curl -O https://raw.githubusercontent.com/efranceschetti/festo-codesys-mcp/main/.claude/skills/writing-st-code/SKILL.mdgit clone --depth 1 https://github.com/efranceschetti/festo-codesys-mcpWrote 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.
[](https://agentmods.dev/skills/efranceschetti/festo-codesys-mcp/writing-st-code)<a href="https://agentmods.dev/skills/efranceschetti/festo-codesys-mcp/writing-st-code"><img src="https://agentmods.dev/badge/skills/efranceschetti/festo-codesys-mcp/writing-st-code.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00094 | $0.00504 |
| Opus 5 | $0.00047 | $0.00252 |
| Sonnet 5 | $0.00019 | $0.00101 |
| Haiku 4.5 | $0.00009 | $0.00050 |
Grade A, and why
writing-st-code 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 7d 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.
What it actually says
Writing Structured Text
Never write ST from memory. Follow this order:
1. Load conventions (once per session)
plc_knowledgeaction=topicconventions, thenabbreviations.- Point lookups while coding:
plc_lookupaction=hungarian (type -> prefix).
2. Reuse before create
plc_libraryaction=search with keywords from the request (e.g. "motor", "valve", "PID").- Match found ->
plc_libraryaction=get, adapt it (rename, adjust IO). Do NOT rewrite from scratch. - No match -> proceed to create. For a new FB also load topic
state-machines.
3. Create with the right tool
- FB ->
create_function_block| cyclic logic ->create_program - ENUM/STRUCT ->
create_data_type| globals ->create_gvl - Servo/stepper motion? STOP — that is the
motion-controlskill (MC_*_Festo blocks, never custom FBs).
4. Verify (mandatory, in order)
review_st_code— naming violations. Fix all.debug_plc_code— runtime bugs (WHILE loops, missing bErr handling, safety gaps). Fix Criticals.- For a full structured review of a file, delegate to the
plc-reviewersubagent.
5. Record in memory
If the code reveals durable project facts (hardware chosen, a new project FB, a design decision), update .claude/memory/ per MEMORY.md rules.
Hard rules: PascalCase + Hungarian, English-only identifiers/comments, FB interface bEnable/bExecute -> bDone/bBusy/bErr/nErrId, nState 0/10-80/90/99. IO access only through GVLs — never hardcode %I/%Q addresses in FBs.
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.
- 7d ago First seen · 33 lines · 94 tokens per session scan A 3177e53b86e3
writing-st-code is a skill published in the GitHub repository efranceschetti/festo-codesys-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 504 once invoked, about $0.0005 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.
Other skills, from other repositories
playwright-cli
Automate browser interactions, test web pages and work with Playwright tests.
playwright-component-testing
Set up component testing with Playwright using a story gallery — scaffold stories and a gallery dev page driven by the built-in mount fixture, no dedicated component-testing runtime. Use when asked to test React or Vue components in isolation with Playwright, or to migrate off @playwright/experimental-ct-react / -vue.
playwright-trace
Inspect Playwright trace files from the command line — list actions, view requests, console, errors, snapshots and screenshots.
browser4-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
qa
QA test your code changes by reading your git diff, choosing the right validation path for frontend/browser and backend changes, and reporting pass/fail with evidence.
smoke-test
Run smoke tests against a deployed or local app based on your git diff. Each test uses Skyvern browser tools (navigate, act, validate, screenshot) with Chrome DevTools MCP as fallback. Posts screenshot evidence as PR comments.