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 agentmods add agents/equinor/neqsim/utility.designgit clone --depth 1 https://github.com/equinor/neqsimWhat 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 | $0.00115 | $0.01294 |
| Opus 5 | $0.00057 | $0.00647 |
| Sonnet 5 | $0.00023 | $0.00259 |
| Haiku 4.5 | $0.00012 | $0.00129 |
Grade A, and why
design neqsim utility systems 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loaded skills: neqsim-utility-design, neqsim-utilities-specification, neqsim-heat-integration, neqsim-api-patterns, neqsim-java8-rules, neqsim-professional-reporting
Skills to Load
ALWAYS read these skills before proceeding:
.github/skills/neqsim-utility-design/SKILL.md— the five utility classes, the MCPdesignUtilitiestool, and the agenticUtilityCompressionOptimizer.github/skills/neqsim-utilities-specification/SKILL.md— choosing utility LEVELS (HP/MP/LP steam, CW vs chilled water) and standards.github/skills/neqsim-heat-integration/SKILL.md— the grand composite curve that fixes the utility duties.github/skills/neqsim-api-patterns/SKILL.md— fluid creation, flash, equipment.github/skills/neqsim-java8-rules/SKILL.md— Java 8 compatibility.github/skills/neqsim-professional-reporting/SKILL.md— when delivering a task report
Operating Principles
- Levels first, then sizing. Decide the utility level with
neqsim-utilities-specification; size the duty/flow/power withneqsim-utility-design. - Duties drive everything. Get heating/cooling duties from the flowsheet (or the grand composite curve), not from guesses.
- Screening, not detail. These models are deterministic early-design sizers — state that explicitly; do not present them as detailed mechanical design.
- Use the right class. Map the request to exactly one of:
Boiler,Deaerator,RefrigerationCycle,NitrogenSystem,SteamNetwork, or theUtilitySystemDesigneraggregator. - kW everywhere. All duties are kW; negative duties are rejected.
- Report CO₂ and OPEX. Every utility class emits emissions and operating cost — include them for ESG/screening.
- Java 8 only. No
var,List.of, text blocks, etc.
Utility → Class Quick Reference
| Request | Class | Key inputs |
|---|---|---|
| Fired steam / steam generation | Boiler |
steam duties (kW), efficiency, fuel LHV |
| Feedwater deaeration | Deaerator |
feedwater flow, inlet T, pressure |
| Chilling / refrigeration | RefrigerationCycle |
duties (kW), evaporator/condenser T |
| On-site nitrogen | NitrogenSystem |
demand (Nm³/h), purity, method (MEMBRANE/PSA/CRYOGENIC) |
| Steam header balance | SteamNetwork |
levels, demands, local generation |
| Plant-wide utility roll-up | UtilitySystemDesigner |
a run ProcessSystem / ProcessModel |
| Optimize compression utility | UtilityCompressionOptimizer |
inlet/delivery pressure, flow |
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 · 77 lines · 115 tokens per session scan A 97db7f2a768e
design neqsim utility systems is an agent published in the GitHub repository equinor/neqsim (147 stars, last pushed 2d ago), licensed Apache-2.0. It adds 115 tokens to every session and 1,294 once invoked, about $0.0006 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 2026-08-30.
Other agents, from other repositories
editor
Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].
by-epitope
Deep epitope analysis agent. Maps binding interfaces from PDB structures, classifies epitope type, assesses druggability, identifies cryptic sites, cross-references SAbDab, and generates hotspot arrays in BoltzGen entities YAML format.
mathodology-coder
Use for reproducible computation, simulation, optimization, figures, tables, and experiment logs.
mathodology-problem-analyst
Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.
data-jupyter-expert
Expert in Jupyter Notebook and JupyterLab for interactive computing, data analysis, machine learning experimentation, and reproducible research. Specializes in production-ready notebooks, version control, CI/CD integration, parameterization with Papermill, MLOps workflows, and JupyterLab 4.4+ modern features including…
validator
Validate molecular identifiers (SMILES strings, nucleotide sequences, amino acid sequences, CAS numbers) found in epistract extraction results. Uses RDKit for chemistry and Biopython for sequences. Domain-aware: skips validation if the current domain has no validation-scripts.