What is cst-sim-agent AGENTS.md?

A repository guide in AGENTS.md for cst-sim-agent, a tool that lets an AI assistant control CST Studio Suite for electromagnetic simulations. It explains the project layout and how its tools connect to the simulation software.

Use it when developing or modifying cst-sim-agent, especially its simulation tools, controllers, connection handling, and Windows-specific automation.

It gives a coding agent the repository-specific rules and structure it should understand before changing code. CST Studio Suite and its COM interface run on Windows.

How valenZW/cst-sim-agent configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to valenZW/cst-sim-agent. 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/valenZW/cst-sim-agent/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/valenZW/cst-sim-agent

Made for: Codex, OpenCode.

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/instructions/valenzw/cst-sim-agent/agents-md/github.svg)](https://agentmods.dev/instructions/valenzw/cst-sim-agent/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/valenzw/cst-sim-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/valenzw/cst-sim-agent/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/valenzw/cst-sim-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/valenzw/cst-sim-agent/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,419 This file is loaded in full into every session.

When invoked 2,419 The same file — it is already loaded in full.

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	$0.02419	$0.02419
Opus 5.5	$0.00968	$0.00968
Sonnet 5.5	$0.00484	$0.00484
Haiku 4.5	$0.00242	$0.00242

Measured 2mo ago against content hash 391a380ec784, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cst-sim-agent 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 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.

AGENTS.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Repo Guide / 仓库指引

Read this before touching any code — it is written for any human or agent that will read or modify this repo. 先读它，再动代码——本文件写给任何将要阅读、修改本仓库的人或 agent。

English Version

One-liner

cst-sim-agent is a Claude Code plugin that turns CST Studio Suite into a conversational electromagnetic-simulation assistant via MCP (FastMCP server) + CST's COM interface. It targets Windows (CST COM is Windows-only).

Repo layout

src/server.py          tool registry: 52 @mcp.tool cst_* tools. Thin wrappers, no business logic.
src/controller.py      CSTController facade: all business logic lives here; tools just forward.
src/connection.py      CST process/project lifecycle (connect, new, open, close, save, project type).
src/dezip.py           Parser for CST's private DE-ZIP container (.cst) — zipfile can't open it.
src/popup_utils.py     Popup detect/read/dismiss. Pure Win32 (ctypes + user32.dll), zero third-party deps.
src/popup_watchdog.py  Popup watchdog: auto-presses Enter on modal dialogs to unblock the solver.
src/version_manager.py Checkpoint versioning: op log + named snapshots + git automation.
hooks/                 4 hooks (pre_vba/post_vba/post_mutate/stop_check); remind only, never block.
skills/cst-expert/     Bundled domain-knowledge skill (SKILL.md + references/).
docs/                  Architecture & verification docs (architecture.md / verification-report.md).

server.py registers (thin); controller.py owns business (thick); connection.py manages lifecycle. New business logic goes in controller, not server.

Call chain

Claude Code
  └─ MCP tool (server.py) → controller.py → connection.py → official cst.interface → CST COM

Two channels:

Official Python API direct calls (parameters, solvers, queries, sweeps, full-history rebuild) — preferred when the official API works.
VBA strings (cst_execute_vba → add_to_history): modeling primitives, materials, ports, SBR, STEP import, frequency. This is the fallback channel and is gated by a static checker.

Read the full file on GitHub · 149 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.

2mo ago First seen · 149 lines · 2,419 tokens per session scan A 391a380ec784

Subscribe to this mod's changes

cst-sim-agent AGENTS.md is an instructions file published in the GitHub repository valenZW/cst-sim-agent (9 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 2,419 tokens to every session, about $0.0097 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.

Scientific

cst-sim-agent AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cst-sim-agent AGENTS.mdvalenZW/cst-sim-agent	Instructions file	9	2mo ago	Apache-2.0	A	2,419	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	1,907	GitHub Copilot

cst-sim-agent: Instructions file for Codex