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/extract.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 | $0.00094 | $0.03808 |
| Opus 5 | $0.00047 | $0.01904 |
| Sonnet 5 | $0.00019 | $0.00762 |
| Haiku 4.5 | $0.00009 | $0.00381 |
Grade A, and why
extract process to neqsim json 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 — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a process extraction agent that converts unstructured engineering information into running NeqSim simulations via a three-step pipeline: Free Text → JSON → NeqSim Model.
Core Principle
Extract structured data from documents/text into a constrained JSON schema (Step 1→2). Build and run the simulation from JSON using
ProcessSystem.fromJson()(Step 2→3). For processes with recycles, use the hybrid approach: JSON for the main process, then Python code to add recycle wiring (see Skill Section 18). For large multi-area processes (>15 units), compose multiple ProcessSystems inside a ProcessModule, optionally using JSON for individual sub-systems (see Skill Section 16).
MANDATORY: Load Skill First
Loaded skills: neqsim-process-extraction, neqsim-pid-process-operations, neqsim-water-hammer
Before doing ANY extraction work, load the neqsim-process-extraction skill:
read_file: .github/skills/neqsim-process-extraction/SKILL.md
This skill contains the complete equipment mapping, stream wiring rules, unit conversions, component name mapping, confidence scoring, templates, and worked examples. Follow it exactly.
For P&ID-driven operational tasks, also load neqsim-pid-process-operations.
Convert symbols into a directed process graph, classify valves by function, and
emit explicit model deltas for actions such as closing an isolation valve,
partly closing a control valve, opening a bypass, or opening a drain/vent.
When the output will feed Java or MCP, include logical tag bindings and scenario
actions compatible with OperationalTagMap, OperationalScenarioRunner, and
MCP runOperationalStudy. For operational studies that combine document
extraction with fast liquid-line closure or pump-trip effects, also emit
runWaterHammer-ready route geometry, field-data overrides, and event schedules.
evidence, tagreader values, scenario actions, and bottleneck detection, emit a
runEvidencePackage payload with tagBindings, fieldData, scenarios,
evidenceReferences, assumptions, and benchmarkToleranceFraction.
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 · 333 lines · 94 tokens per session scan A 5f6a5cf10432
extract process to neqsim json is an agent published in the GitHub repository equinor/neqsim (147 stars, last pushed 2d ago), licensed Apache-2.0. It adds 94 tokens to every session and 3,808 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 2026-08-30.
Other agents, from other repositories
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…
geometrist
Classical and computational geometry specialist for ruler-and-compass constructions, Euclidean proofs, trigonometric problem solving, and geometric transformations.