CAE Agent Hub is a collection of connectors, reusable agent skills, solver-automation workflows, and browser viewers that let coding agents work with engineering simulation software. It is for users of CAE applications and engineering solvers such as Abaqus, ANSYS, LAMMPS, and FreeCAD who work through clients including Codex, Cursor, Claude Code, or Claude Desktop. The catalogue includes 58 skills for these simulation and automation workflows.
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 skills add Cai-aa/CAE-Agent-Hub --skill ansys-structural-workbenchgit clone --depth 1 https://github.com/Cai-aa/CAE-Agent-HubWrote 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/skills/cai-aa/cae-agent-hub/ansys-structural-workbench)<a href="https://agentmods.dev/skills/cai-aa/cae-agent-hub/ansys-structural-workbench"><img src="https://agentmods.dev/badge/skills/cai-aa/cae-agent-hub/ansys-structural-workbench/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/skills/cai-aa/cae-agent-hub/ansys-structural-workbench"><img src="https://agentmods.dev/badge/skills/cai-aa/cae-agent-hub/ansys-structural-workbench.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 109 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00148 | $0.01763 |
| Opus 5.5 | $0.00059 | $0.00705 |
| Sonnet 5.5 | $0.00030 | $0.00353 |
| Haiku 4.5 | $0.00015 | $0.00176 |
Grade A, and why
ansys-structural-workbench 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- ansys-structural-workbench — 91% identical, 25 lines differ
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ANSYS Structural Workbench
Operate Workbench as an engineering workflow with explicit quality gates. Treat the MCP as the execution adapter and this Skill as the analysis, meshing, validation, and reporting policy.
Mandatory book-guidance route
Before inspecting settings for engineering acceptance, mutating the model, meshing, or solving, load ansys-workbench-practical-reference once and use it to select the physics-specific book-derived guidance. This is a required intake gate, not an optional source lookup.
- Every Static Structural task must load
ansys-workbench-static-modeling-reference. - A static task with contact or friction must load both
ansys-workbench-static-modeling-referenceandansys-workbench-nonlinear-contact-reference. - Also load
ansys-workbench-nonlinear-contact-referencefor plasticity, large deflection, buckling, stabilization, changing contact state, or nonlinear convergence. - Modal, transient, explicit, thermal, and optimization tasks load only their matching narrow reference Skill; do not load unrelated book domains.
The book-derived Skills govern modeling assumptions and physical checks. This Skill governs live MCP actions, evidence, and safe execution. Record which guidance Skills were loaded in the task intake or final report. Do not repeatedly re-route after the applicable set has been loaded.
Start safely
- Discover the available Workbench MCP tools and read
references/mcp-adapter.md. Require the registered server nameansys-workbenchunless the user configured an equivalent alias. - Probe both bridge health and live Workbench/Mechanical state. A reachable server is not proof that a project, Model, or analysis is loaded.
- Convert the request into the contract in
references/job-spec.md, including every applicable analysis profile. Use a temporary in-memory object unless a saved spec benefits the task. - Inspect the current project before mutation. Never clear, overwrite, suppress, or replace existing user work without explicit authorization.
- Record assumptions. Stop for missing information only when no conservative, reversible default exists.
What ships with it
30 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.
- agents/openai.yaml 476 B
- assets/structural-analysis-report-template.md 430 B
- references/analysis-profiles.md 2.7 KB
- references/core-workflow.md 2.5 KB
- references/example-bolted-joint.json 1.5 KB
- references/example-clevis-pin.json 3.6 KB
- references/example-contact-results.json 1002 B
- references/example-mesh-loop.json 887 B
- references/example-mesh-quality.json 574 B
- references/example-reference-values.json 459 B
- references/example-report-data.json 749 B
- references/example-units.json 214 B
- references/job-spec.md 3.3 KB
- references/mcp-adapter.md 5.7 KB
- references/mesh-closed-loop.md 2.9 KB
- references/mesh-orchestration.md 3.1 KB
- references/mesh-profiles.md 2.8 KB
- references/quality-gates.md 2.6 KB
- references/solver-diagnostics.md 1.6 KB
- scripts/build_analysis_report.py 1.8 KB runs code
- scripts/calculate_reference_values.py 2.1 KB runs code
- scripts/evaluate_mesh_convergence.py 2.2 KB runs code
- scripts/evaluate_mesh_quality.py 3.1 KB runs code
- scripts/mechanical_mesh_bridge.py 8.0 KB runs code
- scripts/normalize_units.py 2.0 KB runs code
- scripts/recommend_mesh_repairs.py 3.7 KB runs code
- scripts/validate_contact_results.py 3.8 KB runs code
- scripts/validate_job_spec.py 5.8 KB runs code
- scripts/validate_results.py 5.7 KB runs code
- tests/test_scripts.py 2.7 KB runs code
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 Changed · +11 lines · +44 tokens per session 729f2a07a995
- 2mo ago First seen · 105 lines · 104 tokens per session scan A 898561c5caa8
ansys-structural-workbench is a skill published in the GitHub repository Cai-aa/CAE-Agent-Hub (1,296 stars, last pushed 12d ago), licensed MIT. It adds 148 tokens to every session and 1,763 once invoked, about $0.0006 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.
ansys-structural-workbench compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ansys-structural-workbenchCai-aa/CAE-Agent-Hub | Skill | 1.3k | 12d ago | MIT | A | 148 | Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 2d ago | Apache-2.0 | A | 123 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 56k | 6d ago | MIT | A | 44 | Claude Code |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 6d ago | MIT | A | 83 | Claude Code |
| phylogeneticsK-Dense-AI/scientific-agent-skills | Skill | 56k | 6d ago | MIT | A | 71 | Claude Code, Codex |
| research-engineerdavila7/claude-code-templates | Skill | 33k | today | MIT | A | 43 | Claude Code, Codex |
| mapping-to-snomedmaziyarpanahi/openmed | Skill | 5.8k | today | Apache-2.0 | A | 205 | Claude Code |