modelsim

modelsim is a skill for Claude Code, Codex from ProfYangShengXu/nuedc-skills. It costs 54 tokens per session (4,582 once invoked), scanned A, original, MIT.

An HDL simulation guide for ModelSim and QuestaSim, tools that test Verilog or VHDL hardware designs before they run on an FPGA.

In plain words
What is it for?
Use it to compile and simulate Verilog or VHDL, view waveforms, measure coverage, and run gate-level timing simulations.
Why use it?
It gives a workflow for compiling hardware code, inspecting signal waveforms, measuring code coverage, and checking timing. ModelSim-Altera can be used with Quartus for FPGA projects.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions Codex.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is %MODELSIM%\vlog.exe +acc -work work ../src/counter.v.

Good fit Use it to compile and simulate Verilog or VHDL, view waveforms, measure coverage, and run gate-level timing simulations.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/ProfYangShengXu/nuedc-skills
agentmods
npx agentmods add skills/profyangshengxu/nuedc-skills/modelsim

Made for: Claude Code, Codex.

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.

agentmods badge for modelsim

README.md
[![agentmods](https://agentmods.dev/badge/skills/profyangshengxu/nuedc-skills/modelsim/github.svg)](https://agentmods.dev/skills/profyangshengxu/nuedc-skills/modelsim)
Your own site
<a href="https://agentmods.dev/skills/profyangshengxu/nuedc-skills/modelsim"><img src="https://agentmods.dev/badge/skills/profyangshengxu/nuedc-skills/modelsim/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.

agentmods 80×15 button for modelsim

Your own site · 80×15
<a href="https://agentmods.dev/skills/profyangshengxu/nuedc-skills/modelsim"><img src="https://agentmods.dev/badge/skills/profyangshengxu/nuedc-skills/modelsim.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,582 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.04582
Opus 5 $0.00027 $0.02291
Sonnet 5 $0.00011 $0.00916
Haiku 4.5 $0.00005 $0.00458

Measured 12d ago against content hash e9f0d1bbb341, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

modelsim 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 12d 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.

.reasonix/skills/modelsim/SKILL.md · 596 lines

How it starts

The opening of the file, as written. The whole thing — 596 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ModelSim / QuestaSim HDL 仿真全能技能

ModelSim SE/DE / QuestaSim / ModelSim-Altera — FPGA 开发的"逻辑万用表" 写 Verilog/VHDL → 仿真验证 → 波形分析 → 代码覆盖率 → 门级时序仿真


📦 一、版本与安装

1.1 版本对照

版本 来源 限制 推荐场景
ModelSim-Altera Starter Quartus 自带 免费,性能有限 (10K行RTL) 电赛首选 ✅
ModelSim PE Siemens 付费,性能中等 中小项目
ModelSim DE Siemens 付费,高性能 大型项目
QuestaSim Siemens 付费,支持 UVM/SystemVerilog 专业验证

电赛推荐: ModelSim-Altera Starter Edition (随 Quartus II 安装),免费且够用。

1.2 独立安装 ModelSim

下载 (ModelSim PE Student Edition — 免费):
https://www.siemens.com/eda/modelsim-student

安装步骤:
1. 运行 setup.exe → 选择安装路径
2. 选择版本: PE (Personal Edition)
3. 等待安装 (5-10 分钟)
4. 首次运行弹出 License 设置 → 选 "Student Edition"
5. ✔ 完成

1.3 验证安装

:: 检查版本
"C:\modeltech64_10.7\win64\vsim.exe" -version

:: 或 ModelSim-Altera
"C:\intelFPGA\13.1\modelsim_ase\win32aloem\vsim.exe" -version

:: GUI 启动
"C:\intelFPGA\13.1\modelsim_ase\win32aloem\vsim.exe" -gui

🛠 二、CLI 命令速查表

2.1 核心命令

命令 功能 说明
vlib work 创建 work 库 每次新项目第一步
vmap work work 映射逻辑库到物理目录
vlog file.v 编译 Verilog 文件 支持 *.v 通配符
vcom file.vhd 编译 VHDL 文件 支持 *.vhd 通配符
vsim work.module 加载顶层模块仿真 进入仿真模式
vsim -c 命令行模式 (无 GUI) CI/批量使用
vsim -do script.do 加载 DO 脚本运行 自动化
run 10 us 运行仿真 10μs 在仿真模式下执行
run -all 运行直到 $finish
quit -sim 退出仿真 返回命令行
vcover report 覆盖率报告 需启用覆盖率

2.2 一键命令行仿真

:: test_counter.bat — 完整编译仿真脚本
@echo off
set MODELSIM=C:\intelFPGA\13.1\modelsim_ase\win32aloem

:: 1. 创建库
if exist work rmdir /s /q work
%MODELSIM%\vlib.exe work
%MODELSIM%\vmap.exe work work

:: 2. 编译源文件
%MODELSIM%\vlog.exe +acc -work work ../src/counter.v
%MODELSIM%\vlog.exe +acc -work work ../tb/tb_counter.v

:: 3. 仿真 (命令行模式)
%MODELSIM%\vsim.exe -c -do "run -all; quit" work.tb_counter

:: 4. 检查结果 (通过 $display 输出)
echo [OK] Simulation complete

Read the full file on GitHub · 596 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.

  1. 12d ago First seen · 596 lines · 54 tokens per session scan A e9f0d1bbb341

Subscribe to this mod's changes

modelsim is a skill published in the GitHub repository ProfYangShengXu/nuedc-skills (2 stars, last pushed 29d ago), licensed MIT. It adds 54 tokens to every session and 4,582 once invoked, about $0.0003 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.