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 peridigm-evidence-fracturegit 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/peridigm-evidence-fracture)<a href="https://agentmods.dev/skills/cai-aa/cae-agent-hub/peridigm-evidence-fracture"><img src="https://agentmods.dev/badge/skills/cai-aa/cae-agent-hub/peridigm-evidence-fracture/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/peridigm-evidence-fracture"><img src="https://agentmods.dev/badge/skills/cai-aa/cae-agent-hub/peridigm-evidence-fracture.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00060 | $0.00684 |
| Opus 5.5 | $0.00024 | $0.00274 |
| Sonnet 5.5 | $0.00012 | $0.00137 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
peridigm-evidence-fracture 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.
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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Peridigm evidence workflow
The AI client supplies language understanding. The deterministic core supplies context state, compilation, execution and checks; neither silently invokes another model nor treats a successful process as physical validation.
Clarify and confirm
- Call
peridigm_doctorandperidigm_templatesbefore promising a supported simulation. - Call
peridigm_start_context(request, actor)with the actual request. Retain itsrun_id. - Ask the returned questions, grouping at most three important questions per turn. Distinguish missing facts from facts inferable from an explicitly accepted template. Do not invent steel, concrete, damage or contact parameters.
- Pass the actual answer to
peridigm_answer_context. Selectingcompression-two-point-v1ornotched-tension-damage-v1returns its complete synthetic parameters and confirmation hash. Record whether confirmation comes from the human or an AI operator acting within explicit delegation; never label a scripted test or operator answer as a human response. - Submit the returned
confirm_spec_sha256only after review. If the user changes the problem, start a new specification. Preserve the old one.
For CLI use pd-agent start --json '{"request":"..."}', then answer, validate, submit, status, log, repair, collect, and report. CLI and MCP share core.py. The project-local launcher sets the machine config; do not embed server paths or credentials in reusable instructions.
Execute and diagnose
peridigm_validate checks the frozen specification and exact compiled input. peridigm_submit launches a bounded detached worker. Query the same run after client disconnection; never restart just because observation timed out. Cancel only the recorded job with peridigm_cancel.
Use logs to distinguish dependency, syntax, field/node-set, numerical and physical-semantic errors. peridigm_repair only regenerates an invalid deck from an unchanged frozen spec, retaining the previous file and diff. It stops after three attempts. It does not tune constitutive laws, damage, boundaries, velocity or physical end time to force success.
What ships with it
4 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.
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.
- 2d ago First seen · 33 lines · 60 tokens per session scan A 4c659ddee0d4
peridigm-evidence-fracture is a skill published in the GitHub repository Cai-aa/CAE-Agent-Hub (1,079 stars, last pushed 3d ago), licensed MIT. It adds 60 tokens to every session and 684 once invoked, about $0.0002 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 2026-10-16.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
presenting-conference-talks
Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.