generate engineering deliverables

An engineering-output agent that turns a completed NeqSim process model and study class into preliminary design documents. These can include process flow diagrams, utility summaries, alarm and trip schedules, instrument schedules, spare-parts inventories, and fire-scenario information.

In plain words
What is it for?
Use it to prepare preliminary documents for field-development or process-design studies, including process diagrams, utilities, alarms, instruments, spares, fire scenarios, and—where requested—P&ID or DEXPI-related registers.
Why use it?
A process simulation is not yet a usable engineering package, and preparing all supporting schedules and summaries manually takes time. This organizes model results into study-appropriate deliverables while identifying the need for qualified engineering review.

Agent

Install

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.

agentmods
npx agentmods add agents/equinor/neqsim/engineering.deliverables
Clone the repo
git clone --depth 1 https://github.com/equinor/neqsim
Per session 86 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,818 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash 8f52593eb988, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.github/agents/engineering.deliverables.agent.md · 390 lines

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:

  1. Build EngineeringProject with NorsokOffshoreEngineeringBuilder.
  2. Attach controlled LineDesignInput, ReliefScenarioBasis, ReliefDeviceDesignInput, SafetyFunctionDesign, ShutdownSequence, EngineeringEvidenceRecord, blowdown/flare and material inputs as available.
  3. Link dynamic EmergencyShutdownTestResult evidence to each tested sequence.
  4. Export with DexpiEngineeringExporter.
  5. Compile with EngineeringDeliverableCompiler and review engineering-production-readiness.json, engineering-qualification-plan.json, unresolved gaps, engineering registers, dexpi-validation.json and package-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.

Read the full file on GitHub · 390 lines

Changes

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.

  1. 3d ago First seen · 390 lines · 86 tokens per session scan A 8f52593eb988

Subscribe to this mod's changes

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.

Related

Other agents, from other repositories