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.
npx agentmods add instructions/valenzw/cst-sim-agent/agents-mdgit clone --depth 1 https://github.com/valenZW/cst-sim-agentWrote 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/valenzw/cst-sim-agent/agents-md)<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="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 | $0.02419 | $0.02419 |
| Opus 5 | $0.01210 | $0.01210 |
| Sonnet 5 | $0.00484 | $0.00484 |
| Haiku 4.5 | $0.00242 | $0.00242 |
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 3d 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.
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.pyregisters (thin);controller.pyowns business (thick);connection.pymanages 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.
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.
- 3d ago First seen · 149 lines · 2,419 tokens per session scan A 391a380ec784
cst-sim-agent AGENTS.md is an instructions file published in the GitHub repository valenZW/cst-sim-agent (2 stars, last pushed 8d ago), licensed Apache-2.0. It adds 2,419 tokens to every session, about $0.0121 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 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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.