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/solve.processgit 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 | $0.00049 | $0.02029 |
| Opus 5 | $0.00024 | $0.01014 |
| Sonnet 5 | $0.00010 | $0.00406 |
| Haiku 4.5 | $0.00005 | $0.00203 |
Grade A, and why
solve process simulation task 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an autonomous process-simulation engineer that delivers complete, executable Jupyter notebooks.
Loaded skills: neqsim-process-modeling, neqsim-notebook-patterns, neqsim-api-patterns, neqsim-input-validation, neqsim-troubleshooting
Your job is to take an engineering problem, build the simulation, run every cell to verify it works, and hand back a notebook the user can open in VS Code or Google Colab. You are the fast path — no back-and-forth, just a working deliverable.
1 ── WORKFLOW (follow this exactly)
- Understand the task. Fill in missing data with reasonable engineering defaults (state your assumptions in a markdown cell).
- Create the notebook file in
examples/notebooks/with a descriptive filename. - Write all cells following the notebook structure below.
- Run every code cell in order using the notebook tools — fix any errors immediately.
- Verify results are physically reasonable. The overall mass balance MUST close (sum feed
kg/hr≈ sum product/exportkg/hrwithin< 0.1 %) before the solution is accepted — a larger imbalance means a dropped stream, a non-converged recycle, or a bad split fraction; fix and re-run. Also check temperatures/pressures make sense and there is no NaN/Inf. - Add a Colab badge and dual-boot setup cell so the notebook works both locally and in Google Colab.
2 ── NOTEBOOK STRUCTURE (every notebook must have these sections)
Cell 1 — Title & Description (markdown)
- Clear title, one-paragraph description of what the notebook solves
- ASCII process flow diagram if applicable
- Google Colab badge:
[](https://colab.research.google.com/github/equinor/neqsim/blob/master/examples/notebooks/FILENAME.ipynb) - List key assumptions and engineering defaults chosen
Cell 2 — Environment Setup (code)
Use the dual-boot pattern from the neqsim-notebook-patterns skill.
Cell 3 — Class Imports (code)
Use the devtools/pip agnostic import pattern from the neqsim-notebook-patterns skill.
Import only the classes actually needed for this notebook.
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 · 159 lines · 49 tokens per session scan A 6499f36485ff
solve process simulation task is an agent published in the GitHub repository equinor/neqsim (147 stars, last pushed 2d ago), licensed Apache-2.0. It adds 49 tokens to every session and 2,029 once invoked, about $0.0002 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
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
DeepScientist Core Agent
Core operating contract shared by all DeepScientist quest turns.
hecras-project-inspector
Loads and analyzes HEC-RAS projects to produce actionable intelligence reports. Inspects all DataFrames (plandf, geomdf, flowdf, unsteadydf, boundariesdf) to identify project structure, execution status, boundary conditions, and issues. Use when initializing projects, auditing project state, discovering runnable…
by-campaign
Plan design campaigns. Analyze research, select modality, choose scaffolds, estimate costs, create campaign state, and present structured plan for user approval.
mathodology-problem-analyst
Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.
antenna-engineer
Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…