Borrowing it
Nothing to install: this file belongs to Czarnak/tia-portal-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/Czarnak/tia-portal-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/Czarnak/tia-portal-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/instructions/czarnak/tia-portal-mcp/agents-md)<a href="https://agentmods.dev/instructions/czarnak/tia-portal-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/czarnak/tia-portal-mcp/agents-md/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.
<a href="https://agentmods.dev/instructions/czarnak/tia-portal-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/czarnak/tia-portal-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.06577 | $0.06577 |
| Opus 5.5 | $0.02631 | $0.02631 |
| Sonnet 5.5 | $0.01315 | $0.01315 |
| Haiku 4.5 | $0.00658 | $0.00658 |
Grade A, and why
tia-portal-mcp AGENTS.md 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project overview
MCP server for Siemens TIA Portal V21. Exposes 8 tools in read-only, 19 in read-write (startup default), and the same 19 in full mode. Read-write permits in-project edits, compile, and lifecycle with one confirmation prompt per actual lifecycle call. Full runs lifecycle without server elicitation and adds no tools or operations; PLC run/stop was removed. The installer defaults to read-only. Windows-only, requires TIA Portal V21 with Openness enabled. Content tools (content reads and writes, compile_check, and every lifecycle tool except open_project/create_project) act only on the bound project and fail closed with binding_conflict when unbound; only bind_project and open_project accept a public projectPath, and get_project_status takes no arguments.
Two-process architecture (critical to understand)
bind_project retains default/null/explicit bind behavior and adds six explicit inspections:
list_portals, list_server_connections, list_server_groups, list_server_projects,
list_local_sessions, get_lock_state. Current counts are 8/19/19; PR3 had 7/17/17. Discovery never adopts; inventory
uses persistent Portal-only attachment, never switches/adopts/opens a project. Selectors are exact
raw-key validated; root group requires {isRoot:true,name:null}. Verified foreign-PID refusal is
local/NotSent and preserves binding/cursors; genuine context/transport loss still invalidates.
Sessions cover currentMachineCurrentUser; locks are non-atomic observations. Typed inspection
is conditional inside the budgeted binding value (60,000/180,000 characters by default), not a new envelope.
Inspection adds no lifecycle elicitation/write audit or session mutation.
See Multiuser reference.
PR3 received exact live authorization on 2026-10-06. All six inspection actions succeeded against
three disposable session copies and a standalone AP21; all five remote inventories also succeeded
with zero open projects. Healthy verified binding/cursors and worker-loss invalidation/recovery
were observed. The maintainer accepted PR3 live testing as finished and passed on 2026-10-06;
unexecuted cases are retained as non-blocking evidence limitations in the
live acceptance report.
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.
- yesterday Changed · +2 lines · +547 tokens per session 9ac29c3cbb7e
- 2d ago Changed · +1 lines · +13 tokens per session 3711950058ef
- 3d ago Changed · +6 lines · +99 tokens per session 7c02f443f496
- 4d ago Changed · +127 tokens per session e8acb008dfae
- 5d ago Changed · +92 tokens per session 3e97a85a4fd0
- 7d ago Changed · +1 lines · +333 tokens per session cb7c5e9dc3b5
- 11d ago Changed · +1 lines · +254 tokens per session 826328e281d5
- 12d ago Changed · +1 lines · +68 tokens per session 121b41917f41
- 13d ago Changed · +6 lines · +447 tokens per session 7ecbc57574eb
- 15d ago First seen · 214 lines · 4,597 tokens per session scan A 38bfdec5ee66
tia-portal-mcp AGENTS.md is an instructions file published in the GitHub repository Czarnak/tia-portal-mcp (95 stars, last pushed yesterday), licensed MIT. It adds 6,577 tokens to every session, about $0.0263 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.