workbench-sim

A connection between an AI coding agent and Ansys Workbench, an engineering program used for computer-based simulation and analysis. It supports running Workbench journals, inspecting projects, keeping sessions open, handing work to Mechanical, and reporting files and results.

In plain words
What is it for?
Use it to inspect Workbench projects, run journal scripts, manage persistent sessions, pass work to Mechanical, and collect simulation artifacts and results.
Why use it?
It removes the need to carry out every Workbench operation manually from outside the coding agent. It also provides bounded execution and troubleshooting guidance for these engineering tasks.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/svd-ai-lab/sim-plugin-workbench/workbench
Any agent
npx skills add svd-ai-lab/sim-plugin-workbench --skill workbench
Clone the repo
git clone --depth 1 https://github.com/svd-ai-lab/sim-plugin-workbench

Made for: Claude Code, Codex.

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,324 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00070 $0.01324
Opus 5 $0.00035 $0.00662
Sonnet 5 $0.00014 $0.00265
Haiku 4.5 $0.00007 $0.00132

Measured 2d ago against content hash 59066eceb457, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workbench-sim 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 2d ago.

The scan reads SKILL.md. This mod also ships 8 executable files (base/snippets/01_smoke_test.py, base/snippets/02_create_static_structural.py, base/snippets/04_run_journal.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

src/sim_plugin_workbench/_skills/workbench/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

workbench-sim

You are connected to Ansys Workbench via sim-cli. This file is the index. It tells you where to look for actual content — it does not contain the content itself.

The /connect response told you which active layers apply via:

"skills": {
  "root":               "<sim-skills>/workbench",
  "active_sdk_layer":   "0.4",
  "active_solver_layer": "24.1"
}

Always read the index for base/, then your active sdk/<version>/, then your active solver/<version>/. Later layers override earlier ones on identically-named files.


base/ — always relevant

Concepts, API patterns, and version-agnostic reference:

Path What's there
base/reference/pyworkbench_api.md PyWorkbench SDK API surface: launch_workbench, run_script_string, upload_file, download_file, start_mechanical_server, start_fluent_server. Read first.
base/reference/journal_scripting.md IronPython .wbjn scripting reference: SetScriptVersion, GetTemplate, CreateSystem, GetContainer, and the result file convention.
base/reference/system_templates.md Live template discovery and resolver workflow. Template names are product/configuration dependent; treat any examples as non-authoritative.
base/reference/file_transfer.md File upload/download patterns between client and server.
base/reference/sub_solver_integration.md Starting PyMechanical, PyFluent, PySherlock servers from within a Workbench session.
base/snippets/ Numbered IronPython journal snippets (01 through 05). Each writes results to %TEMP%/sim_wb_result.json.
base/examples/ Official PyWorkbench examples from pyansys.com — Fluent workflow, PyMechanical integration, logging, cooled turbine blade, cyclic symmetry, axisymmetric rotor, material designer.
base/workflows/static_structural/ 6-step Static Structural walkthrough (Engineering Data → Geometry → Model → Setup → Solution → Results). Per-cell API reference + gotchas + executable walk_workflow.py.
base/workflows/project_review_loop.md Required checkpoint loop: inspect health, project identity, systems summary, then run one bounded journal step.
base/workflows/debug_failed_exec.md Failure triage loop for failed Workbench snippets and RunWB2 journals.
base/workflows/mechanical_handoff.md Workbench-to-Mechanical checklist for Static Structural workflows.
base/known_issues.md Vendor quirks, SDK version constraints, IronPython limitations.

Read the full file on GitHub · 101 lines

Files

What ships with it

33 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 101 lines · 70 tokens per session scan A 59066eceb457

Subscribe to this mod's changes

workbench-sim is a skill published in the GitHub repository svd-ai-lab/sim-plugin-workbench (4 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,324 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.

Related

Other skills, from other repositories

abaqus-sim

Use when the user asks Codex, Claude Code, ChatGPT-style coding agents, or another AI agent to automate, inspect, run, or debug Abaqus through sim-cli. Supports Abaqus/CAE noGUI workflows, batch jobs, model inspection, ODB diagnostics, bounded execution, artifact reporting, and troubleshooting. Requires a user-owned…

svd-ai-lab/sim-plugin-abaqus · 77 tokens

openfoam-sim

Use when the user asks Codex, Claude Code, or another AI coding agent to run, inspect, or debug OpenFOAM cases through sim-cli. Supports case checks, solver execution, log inspection, result artifacts, replayable CFD workflows, and benchmark tasks.

svd-ai-lab/sim-plugin-openfoam · 58 tokens

pymapdl-cli

How to use the PyMAPDL command-line interface to start, stop, list, and execute commands on MAPDL instances from a terminal. Use this skill whenever the user wants to control MAPDL from the command line, run APDL commands via the shell, manage running MAPDL processes, script MAPDL workflows without writing Python, or…

ansys/pymapdl · 90 tokens

comsol-sim

Use when the user asks Codex, Claude Code, ChatGPT-style coding agents, or another AI agent to build, inspect, run, debug, or revise COMSOL Multiphysics / COMSOL Desktop models. Choose the simplest real COMSOL control path for the task: saved .mph inspection, local COMSOL documentation, direct COMSOL executables…

svd-ai-lab/sim-plugin-comsol · 134 tokens

aieng-cad-cae-copilot

MCP-first evidence workflow for AIENG CAD/CAE setup, solver preflight, approval-gated solver execution, and result extraction. Use when the user asks to inspect CAE readiness, patch setup, prepare/run CalculiX, or report stress/displacement evidence.

armpro24-blip/cad-cae-copilot · 65 tokens

aieng-closed-loop-copilot

MCP-first closed-loop CAD/CAE copilot skill for improving an existing solved design against explicit targets. Use when the user asks for bounded design iteration using editable CAD parameters, solver reruns, and evidence-backed comparison.

armpro24-blip/cad-cae-copilot · 54 tokens