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 Suzhou-Tongyuan/sysplorer-mcp-server --skill ty-mechanical-modelinggit clone --depth 1 https://github.com/Suzhou-Tongyuan/sysplorer-mcp-serverWrote 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/suzhou-tongyuan/sysplorer-mcp-server/ty-mechanical-modeling)<a href="https://agentmods.dev/skills/suzhou-tongyuan/sysplorer-mcp-server/ty-mechanical-modeling"><img src="https://agentmods.dev/badge/skills/suzhou-tongyuan/sysplorer-mcp-server/ty-mechanical-modeling/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/suzhou-tongyuan/sysplorer-mcp-server/ty-mechanical-modeling"><img src="https://agentmods.dev/badge/skills/suzhou-tongyuan/sysplorer-mcp-server/ty-mechanical-modeling.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 | $0.00132 | $0.02296 |
| Opus 5.5 | $0.00053 | $0.00918 |
| Sonnet 5.5 | $0.00026 | $0.00459 |
| Haiku 4.5 | $0.00013 | $0.00230 |
Grade A, and why
ty-mechanical-modeling 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 19d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TY Mechanical Modeling
Use this only as a thin domain add-on to ty-sysplorer-modeling-rules. The parent skill owns routing, seven gates, layout timing, repair loop, and delivery evidence.
Common authority: ../ty-sysplorer-modeling-rules/references/shared-standards.md owns MCP 0.4 session, tool, error and retry contracts; ../ty-sysplorer-modeling-rules/workflows/seven-gates-validation.md owns the seven gates, validation depth and Gate 6. This domain add-on supplies checks, not a second execution pipeline.
- Respect explicit choices and effective prior context. Without a selected library, the parent first checks whether the standard library meets the requirements; keep sufficient standard components and add commercial components only for evidenced gaps. A documentation or tool failure is not a functional gap. This Modelica library combination is not Modelica/Sysblock mixed modeling.
- The domain library list constrains only this skill's responsible subsystem. Preserve selected standard components and other domains in the project library set; confirm cross-domain interfaces instead of deleting them.
- Commercial-library paths, including standard/commercial combinations, use
Modelica 4.0.0.TY.1. Record a conflicting project version without silently rewriting dependencies. - Inherit requested check/translate/simulate/result/plot/animation scope; unrequested actions are
not_required. Formal reports and report templates are used only when requested; ordinary delivery uses concise evidence and applicable status fields. - Existing fault diagnosis is led by the parent's debugging route; provide domain evidence and minimal repair without restarting model construction. A failure during new construction stays in its originating workflow and returns to its failed stage after repair.
- Gate 6 applies to newly created or actually modified graphical objects, including MCP automatic layout changes. Read-only, Documentation-only, pure code without graphical objects, and tasks that do not change graphical targets use
not_required; untouched inherited objects/layers are not expanded. - Structured diagram evidence is the common basis; images supplement it when requested or useful and available. Preserve explicit image requests as pending when unavailable and never claim visual inspection from text. Visual layout defects do not block check, translation or simulation; annotation syntax/structure errors are handled by model check. Applicable Gate 6 remains required for complete graphical delivery.
- MCP 0.4 check/translate/simulate can automatically write and reload a user
.moeven withoutreload_mo_path. Read-only diagnosis must assess that boundary before calling them, use an authorized copy when possible, or report the limitation; do not promise a write-free check or bypass dedicated tools.
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.
- agents/openai.yaml 754 B
- references/acceptance-checklist.md 3.3 KB
- references/ai-execution-spec.md 1.1 KB
- references/common-errors.md 2.9 KB
- references/component-map.md 9.7 KB
- references/error-repair-playbook.md 3.3 KB
- references/mcp-modeling-toolkit.md 5.4 KB
- references/parameter-rules.md 3.3 KB
- references/phase-output-templates.md 2.2 KB
- references/requirement-map.md 3.5 KB
- references/shared-standards.md 1.8 KB
- references/standard-input-checklist.md 1.4 KB
- references/validation-rules.md 7.8 KB
- scripts/doc_to_md.py 7.3 KB runs code
- scripts/init_modeling_project.py 1.2 KB runs code
- scripts/pdf_to_md.py 26 KB runs code
- scripts/ppt_to_md.py 9.9 KB runs code
- scripts/README.md 1.8 KB
- scripts/web_to_md.cjs 27 KB runs code
- scripts/web_to_md.py 26 KB runs code
- skill_info.json 1.0 KB
- SKILL_ZH.md 8.9 KB
- templates/delivery-template.md 1015 B
- templates/model-skeletons/mechanical-system-base.example.mo 806 B
- templates/reports/simulation-report-template.md 1001 B
- templates/scenarios/mechanical-system-min-loop.example.json 818 B
- templates/scenarios/user-input-minimum-form.md 2.8 KB
- templates/task-output-template.md 1.1 KB
- workflows/build-from-scenario.md 3.2 KB
- workflows/repair-existing-model.md 2.2 KB
- workflows/verify-example.md 1.7 KB
- 使用说明.md 2.0 KB
- 版本说明.md 4.1 KB
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.
- 19d ago First seen · 101 lines · 132 tokens per session scan A aed0e9e52b0a
ty-mechanical-modeling is a skill published in the GitHub repository Suzhou-Tongyuan/sysplorer-mcp-server (10 stars, last pushed 20d ago), licensed MIT. It adds 132 tokens to every session and 2,296 once invoked, about $0.0005 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 2026-10-13.
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.