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 valenZW/cst-sim-agent --skill cst-expertgit clone --depth 1 https://github.com/valenZW/cst-sim-agentWrote 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/valenzw/cst-sim-agent/cst-expert)<a href="https://agentmods.dev/skills/valenzw/cst-sim-agent/cst-expert"><img src="https://agentmods.dev/badge/skills/valenzw/cst-sim-agent/cst-expert.svg" alt="Measured on agentmods" 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 | $0.00105 | $0.01374 |
| Opus 5 | $0.00053 | $0.00687 |
| Sonnet 5 | $0.00021 | $0.00275 |
| Haiku 4.5 | $0.00011 | $0.00137 |
Grade A, and why
cst-expert 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 8d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CST Expert — 全场景仿真专家
当前状态
- 插件工具组1-8 已在真实 CST 上实测通过(连接/保存/求解器/弹窗/查询/SBR/建模/材料/参数扫描)。
- 本插件面向通用 CST 仿真自动化,适用于任何 CST 建模/求解/后处理任务。
核心原则
- 始终 Python 驱动 CST:
DesignEnvironment → Project → Model3D.add_to_history(VBA字符串),不生成独立 VBA 宏文件。 - 操作前先查参考案例:读
example_index.md找最接近的官方案例。 - VBA 语法先验证再执行:涉及具体对象时先查
vba_syntax/对应文件。 - 所有关键操作记录日志。
- 输出语言:思考、方案说明、询问确认中英文均可(优先与用户所用语言一致)。
- 🔴 关键操作后立即保存:
cst_save_project写盘并验证文件大小(cst_disconnect写死 save=False,CST 不自动保存,崩溃丢全部内存修改)。
铁律速查表(详细规则见 references/vba-rules.md)
| 铁律 | 概要 |
|---|---|
🔴 写 VBA 前必查 vba_syntax/ |
凭记忆写 CST VBA = 违规;先读插件内 references/knowledge/vba_syntax/ 对应文件 |
| 🔴 四条记录铁律 | ①错误原文禁摘写 ②排障第0步确认输入存在 ③超时≠故障 ④VBA后必查消息+状态 |
| 🔴 代码注释规范 | 改 src/*.py 必带【文件思路】+行注释(中英文均可)+Bug编号引用 |
| 🔴 兜底查文档 | 语法库查不到 → 查 CST 官方文档(Online Help),禁止凭记忆盲试 |
| ⚠️ MCP 不可用排障 | 先读 stderr jsonl 日志,不猜;勿用 cache 目录作判据 |
机制化:以上铁律已由插件 hooks 按需注入——仅当调用
cst_*工具时触发:写 VBA 前(pre_vba,用户可见提醒)、VBA 后(post_vba,含下次写前查库)、关键操作后(post_mutate)、涉 CST 会话收尾(stop_check,读 transcript 判断),见插件hooks/目录。不调用 cst-sim-agent 不注入;hook 只提醒不阻断;铁律的详细理由与扩展规则仍以 references 为准。
任务收尾流程(每次仿真后强制执行)
- 从本轮会话记录识别经验增量:新错误、新 VBA 对象/方法、新工作流、新求解器。
- 按维度写入插件内
references/knowledge/对应文件(避坑清单 / vba_syntax / 经验库模板)。 - 向用户逐条确认后写入,每条附时间戳;禁止无时间戳无来源的裸经验。
案例深度学习流程(任务启动时执行)
匹配案例(example_index.md)→ 读缓存深潜或提取案例摘要 → 应用经验到任务。详细 Step A/B/C 见 references/case-study-flow.md。
知识库导航
| 资源 | 路径 | 用途 |
|---|---|---|
| 铁律细节 | references/vba-rules.md |
四条铁律全文、代码注释规范、排障、兜底查询顺序 |
| 案例流程 | references/case-study-flow.md |
案例深度学习、extract_case 工具用法 |
| 官方文档查询 | references/official-docs.md |
文档地图、查询路径、已证实官方结论 |
| 通用避坑 | references/common-pitfalls.md |
通用 CST 操作避坑清单(端口/网格/求解器/API 陷阱) |
| 增量经验模板 | references/best-practices-template.md |
空白经验库模板,供用户 DIY 追加 |
| 语法库 | references/knowledge/vba_syntax/ |
8 域 VBA 权威语法(materials/ports/solver/mesh/boundaries/monitors/cad_import/postproc) |
| 案例索引 | references/knowledge/example_index.md |
158 案例索引(领域+标签+求解器) |
| 深潜缓存 | references/knowledge/on_demand_dives/ |
35 例已提取深度分析 |
| 静态手册 | references/knowledge/仿真经验手册.md |
跨领域经验提炼 |
What ships with it
51 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.
- references/best-practices-template.md 935 B
- references/case-study-flow.md 3.0 KB
- references/common-pitfalls.md 18 KB
- references/knowledge/case_fingerprints.md 24 KB
- references/knowledge/example_index.md 18 KB
- references/knowledge/on_demand_dives/TID_100.md 1.0 KB
- references/knowledge/on_demand_dives/TID_101.md 2.2 KB
- references/knowledge/on_demand_dives/TID_102.md 1.6 KB
- references/knowledge/on_demand_dives/TID_103.md 1.6 KB
- references/knowledge/on_demand_dives/TID_104.md 2.5 KB
- references/knowledge/on_demand_dives/TID_110.md 984 B
- references/knowledge/on_demand_dives/TID_121.md 273 B
- references/knowledge/on_demand_dives/TID_133.md 292 B
- references/knowledge/on_demand_dives/TID_150.md 2.4 KB
- references/knowledge/on_demand_dives/TID_174.md 237 B
- references/knowledge/on_demand_dives/TID_260.md 1.1 KB
- references/knowledge/on_demand_dives/TID_261.md 1.2 KB
- references/knowledge/on_demand_dives/TID_262.md 909 B
- references/knowledge/on_demand_dives/TID_263.md 887 B
- references/knowledge/on_demand_dives/TID_264.md 1.3 KB
- references/knowledge/on_demand_dives/TID_280.md 1.9 KB
- references/knowledge/on_demand_dives/TID_282.md 1.8 KB
- references/knowledge/on_demand_dives/TID_292.md 2.1 KB
- references/knowledge/on_demand_dives/TID_313.md 2.0 KB
- references/knowledge/on_demand_dives/TID_331.md 1.5 KB
- references/knowledge/on_demand_dives/TID_332.md 1.4 KB
- references/knowledge/on_demand_dives/TID_342.md 1.9 KB
- references/knowledge/on_demand_dives/TID_343.md 1.4 KB
- references/knowledge/on_demand_dives/TID_354.md 2.1 KB
- references/knowledge/on_demand_dives/TID_360.md 2.1 KB
- references/knowledge/on_demand_dives/TID_361.md 2.2 KB
- references/knowledge/on_demand_dives/TID_364.md 2.0 KB
- references/knowledge/on_demand_dives/TID_370.md 1.4 KB
- references/knowledge/on_demand_dives/TID_372.md 2.4 KB
- references/knowledge/on_demand_dives/TID_374.md 4.8 KB
- references/knowledge/on_demand_dives/TID_379.md 1.4 KB
- references/knowledge/on_demand_dives/TID_66.md 5.2 KB
- references/knowledge/on_demand_dives/TID_67.md 2.3 KB
- references/knowledge/on_demand_dives/TID_93.md 1.3 KB
- references/knowledge/on_demand_dives/TID_94.md 1.2 KB
- references/knowledge/vba_syntax/boundaries.md 2.9 KB
- references/knowledge/vba_syntax/cad_import.md 2.4 KB
- references/knowledge/vba_syntax/materials.md 2.5 KB
- references/knowledge/vba_syntax/mesh.md 2.9 KB
- references/knowledge/vba_syntax/monitors.md 3.0 KB
- references/knowledge/vba_syntax/ports.md 4.7 KB
- references/knowledge/vba_syntax/postproc.md 3.9 KB
- references/knowledge/vba_syntax/solver.md 8.7 KB
- references/knowledge/仿真经验手册.md 13 KB
- references/official-docs.md 3.9 KB
- references/vba-rules.md 6.6 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.
- 8d ago First seen · 63 lines · 105 tokens per session scan A 54a80be1290f
cst-expert is a skill published in the GitHub repository valenZW/cst-sim-agent (3 stars, last pushed 13d ago), licensed Apache-2.0. It adds 105 tokens to every session and 1,374 once invoked, about $0.0005 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.
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
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for 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
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
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.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…