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 ta-vehicle-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/ta-vehicle-modeling)<a href="https://agentmods.dev/skills/suzhou-tongyuan/sysplorer-mcp-server/ta-vehicle-modeling"><img src="https://agentmods.dev/badge/skills/suzhou-tongyuan/sysplorer-mcp-server/ta-vehicle-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/ta-vehicle-modeling"><img src="https://agentmods.dev/badge/skills/suzhou-tongyuan/sysplorer-mcp-server/ta-vehicle-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 | $0.00235 | $0.02534 |
| Opus 5.5 | $0.00094 | $0.01014 |
| Sonnet 5.5 | $0.00047 | $0.00507 |
| Haiku 4.5 | $0.00023 | $0.00253 |
Grade A, and why
ta-vehicle-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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TA Vehicle 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, Sysplorer safety rules, and delivery evidence. This skill adds vehicle-domain entry routing, TA six-library vehicle modeling decisions, library boundaries, examples, and validation focus.
Entry Contract
Treat this skill as mandatory for any Sysplorer task whose target object is a vehicle, whole vehicle, automotive subsystem, or vehicle operating scenario, even when the user does not name a TA library.
Trigger examples include:
- Whole-vehicle or subsystem construction, repair, packaging, review, layout-annotation authoring, translation, simulation, or result validation.
- Lumped-parameter, point-mass, equivalent-mass, coast-down, acceleration, braking, drive-cycle, range, economy, handling, ride, thermal-management, engine, battery, electrical-load, chassis, tire, suspension, steering, brake, driveline, powertrain, and motor-drive vehicle tasks.
- Requests that say only "车辆模型", "整车模型", "滑行工况", "动力性", "经济性", "续航", "操稳", "平顺性", "热管理", "发动机", "电池", "低压电器", or similar vehicle-domain wording.
After triggering, first apply ty-sysplorer-modeling-rules for Modelica/Sysblock/hybrid routing. Then use this skill to decide whether the implementation should use TA six-library components, a simpler Modelica/MSL/custom lumped model, or a documented fallback because TA evidence is unavailable or out of scope. Do not skip this skill merely because the user asks for a "simple" or "lumped-parameter" vehicle model.
Hard Constraints
Treat these as blocking requirements, not preferences:
- For Sysplorer vehicle tasks, stay in the Sysplorer MCP / ModelingPy tool domain. Do not route to Syslab skills or Syslab tools unless the user explicitly asks for Syslab.
- Do not directly copy or
extendsa complete official example, complete vehicle architecture, complete subsystem template, or complete sample deliverable as a new user deliverable. - Modeling difficulty, missing internal signal wiring, failed repair attempts, or schedule pressure never relaxes the previous rule. If blocked, reduce scope, hand-build the visible topology, or report the blocker; do not hide the requested model behind an inherited complete template.
- Deliverable source must expose the requested vehicle topology through explicit component instances and
connect(...)statements unless the task is only to verify or explain an existing example. - Before
CheckModel,TranslateModel, orSimulateModelon a deliverable.mo, runscripts/audit_modelica_source.pywhen a file path exists. For packaged models, pass--dependency-rootwith the already authorized top-level package directory so the audit can read enclosingpackage.modependencies; without that option it reads only the model file. Never infer an authorization root or search outside it. A failed audit is a stop condition, not a warning. - Before simulation, verify that the requested end time is actually bound to the tool/model stop-time setting. Do not use result probe times such as
target_timeas a substitute for stop time unless the active tool schema documents that mapping. - Final delivery must state the official/example usage status:
reference only,directly reused existing example, ornot used.directly reused existing examplecannot be reported as a newly built deliverable. - Apply parent Gate 6 to graphical objects actually created or changed, including automatic layout writes. Use hierarchy,
Placement,Line(...), endpoints, and layout diagnostics as structural evidence; image export/inspection follows user needs and available capability. Recordnot_requiredfor read-only, Documentation-only, code-only without graphical objects, or unchanged graphical targets. Do not expand unchanged inherited levels or claim visual inspection without viewing images.
What ships with it
41 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 842 B
- references/acceptance-checklist.md 1.1 KB
- references/build-rules.md 4.4 KB
- references/combination-rules.md 1.2 KB
- references/common-errors.md 7.8 KB
- references/diagram-layout-rules.md 7.0 KB
- references/error-repair-playbook.md 8.1 KB
- references/library-cards/TABattery.md 2.6 KB
- references/library-cards/TADynamics.md 3.9 KB
- references/library-cards/TAEconomy.md 3.6 KB
- references/library-cards/TAElectronic.md 3.0 KB
- references/library-cards/TAEngine.md 2.4 KB
- references/library-cards/TAThermalSystem.md 3.5 KB
- references/library-selection.md 3.1 KB
- references/output-contract.md 2.7 KB
- references/package-design.md 4.2 KB
- references/parameter-rules.md 1.8 KB
- references/preflight-checklist.md 3.8 KB
- references/requirement-map.md 3.0 KB
- references/validation-rules.md 3.2 KB
- scripts/audit_modelica_source.py 14 KB runs code
- 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 3.1 KB
- scripts/web_to_md.cjs 27 KB runs code
- scripts/web_to_md.py 26 KB runs code
- skill_info.json 1.1 KB
- SKILL_ZH.md 9.7 KB
- templates/reports/delivery-report-template.md 1.2 KB
- templates/reports/result-summary-template.md 1.0 KB
- templates/scenarios/case-selection-template.md 1.3 KB
- templates/scenarios/dynamics-whole-vehicle-skeleton.md 1.9 KB
- templates/scenarios/economy-main-framework.md 1.9 KB
- templates/scenarios/thermal-management-loop-skeleton.md 2.1 KB
- workflows/build-from-scenario.md 4.2 KB
- workflows/repair-existing-model.md 2.2 KB
- workflows/verify-example.md 1.8 KB
- 使用说明.md 2.0 KB
- 版本说明.md 1.7 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 · 110 lines · 235 tokens per session scan A 6787f8225979
ta-vehicle-modeling is a skill published in the GitHub repository Suzhou-Tongyuan/sysplorer-mcp-server (10 stars, last pushed 20d ago), licensed MIT. It adds 235 tokens to every session and 2,534 once invoked, about $0.0009 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.