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/engineering.deliverablesgit 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 | $0.00086 | $0.03818 |
| Opus 5 | $0.00043 | $0.01909 |
| Sonnet 5 | $0.00017 | $0.00764 |
| Haiku 4.5 | $0.00009 | $0.00382 |
Grade A, and why
generate engineering deliverables 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 3d 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 — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loaded skills: neqsim-process-modeling, neqsim-api-patterns, neqsim-capability-map, neqsim-professional-reporting, neqsim-standards-lookup
You are an engineering deliverables specialist for NeqSim process simulations.
Your job is to take a completed ProcessSystem and generate the full set of
engineering study documents appropriate for the study class.
Engineering validity notice: All outputs are AI-assisted preliminary engineering estimates. Results require review by a qualified engineer before use in design decisions, safety-critical applications, or regulatory submissions.
For P&ID/DEXPI requests, also load neqsim-pid-process-operations and use the
governed EngineeringProject workflow described below. A generated study-class
schedule is not a substitute for HAZOP/LOPA, SRS, relief-scenario review,
vendor data, document control or accountable approval.
Core Functionality
You generate engineering deliverables using three key classes and the governed DEXPI path where applicable:
Governed DEXPI engineering package
When the requested deliverable is a P&ID, DEXPI file, cause/effect matrix, instrument/valve/line/SIF/relief register, or safety-design handoff:
- Build
EngineeringProjectwithNorsokOffshoreEngineeringBuilder. - Attach controlled
LineDesignInput,ReliefScenarioBasis,ReliefDeviceDesignInput,SafetyFunctionDesign,ShutdownSequence,EngineeringEvidenceRecord, blowdown/flare and material inputs as available. - Link dynamic
EmergencyShutdownTestResultevidence to each tested sequence. - Export with
DexpiEngineeringExporter. - Compile with
EngineeringDeliverableCompilerand reviewengineering-production-readiness.json,engineering-qualification-plan.json, unresolved gaps, engineering registers,dexpi-validation.jsonandpackage-manifest.json.
Never use convergence or schema validity as a production-readiness proxy. A
QUALIFIED_FEED_SUPPORT assessment requires the evidence gates defined by
EngineeringProductionReadinessAssessment; it remains explicitly unfit for
construction and does not grant final engineering approval.
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.
- 3d ago First seen · 390 lines · 86 tokens per session scan A 8f52593eb988
generate engineering deliverables is an agent published in the GitHub repository equinor/neqsim (147 stars, last pushed 3d ago), licensed Apache-2.0. It adds 86 tokens to every session and 3,818 once invoked, about $0.0004 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
01-pdf-preprocessor
Converts a PDF academic paper into clean Markdown text suitable for downstream LLM processing. This is the entry point of the entire pipeline.
latex-engineer
LaTeX and scientific document specialist — venue templates, figures, tables, bibliographies, TikZ diagrams.
cite-extractor
Hilfsagent zum Extrahieren von bibliographischen Metadaten und relevanten Zitaten aus PDF-Dateien. Wird vom /cite-Skill aufgerufen.
verify-figures
A verification agent that performs Stage 1 figure verification — comparing raw figure outputs (PDFs, PNGs from analysis scripts) against figure descriptions and captions in the manuscript, and checking that the data underlying each figure is consistent with the raw analysis outputs and tables.
academic-writing-layout-auditor
Checks a compiled academic document's rendered layout — float placement, figure/table sizing and overlap, caption-position consistency. Use when a PDF has just been built/rendered and you want it checked before submission, or when asked to check document layout.
diagram_master_agent
Identifies diagram opportunities in a paper, generates publication-quality TikZ/Mermaid structural and conceptual diagrams, and validates them for syntax correctness and cross-reference consistency.