run neqsim safety and depressuring simulation

run neqsim safety and depressuring simulation is an agent for Claude Code from equinor/neqsim. It costs 79 tokens per session (3,849 once invoked), scanned A, original, Apache-2.0.

An agent for process-safety simulations with NeqSim. Process safety covers events such as vessel blowdown, pressure relief, trapped-liquid heating, gas dispersion, and hazardous operating scenarios.

In plain words
What is it for?
Use it for depressurization, relief-valve sizing, flare studies, fire-rupture screening, safety-envelope calculations, and HAZOP scenario generation.
Why use it?
It helps turn equipment events or operating actions into calculated source terms, safety checks, and consequence-analysis inputs.

Agent for Claude Code

Written for Claude Code: argument-hint in frontmatter.

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/safety.depressuring
Clone the repo
git clone --depth 1 https://github.com/equinor/neqsim

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for run neqsim safety and depressuring simulation

README.md
[![agentmods](https://agentmods.dev/badge/agents/equinor/neqsim/safety.depressuring.svg)](https://agentmods.dev/agents/equinor/neqsim/safety.depressuring)
Your own site
<a href="https://agentmods.dev/agents/equinor/neqsim/safety.depressuring"><img src="https://agentmods.dev/badge/agents/equinor/neqsim/safety.depressuring.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,849 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 5.1 $0.00079 $0.03849
Opus 5 $0.00039 $0.01924
Sonnet 5 $0.00016 $0.00770
Haiku 4.5 $0.00008 $0.00385

Measured 6d ago against content hash 9dcd987523e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

run neqsim safety and depressuring simulation 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 6d 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/safety.depressuring.agent.md · 365 lines

How it starts

The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a process safety engineer for NeqSim.

Loaded skills: neqsim-process-safety, neqsim-trapped-liquid-fire-rupture, neqsim-depressurization-mdmt, neqsim-relief-flare-network, neqsim-self-heating-ignition, neqsim-stid-retriever, neqsim-technical-document-reading, neqsim-pid-process-operations, neqsim-water-hammer

Primary Objective

Perform process safety calculations — depressurization, relief sizing, source terms, safety envelopes, SIL classification, HAZOP scenario generation — and produce working code with validated results.

When a safety case starts from a P&ID action such as closing a valve, opening a vent, isolating a section, or blowing down to flare, use neqsim-pid-process-operations to define the boundary, valve action, control logic, and historian evidence before running the safety calculation. For reusable pre-screens, express the initiating valve or field-data action with OperationalScenarioRunner or MCP runOperationalStudy, then hand the resulting source terms and boundary state to the depressurization, relief, or flare model. For liquid-filled or liquid-rich lines where the initiating event is fast closure, pump trip, or check-valve slam, first screen hydraulic surge with neqsim-water-hammer / MCP runWaterHammer and carry pressure-envelope findings into the safety assumptions and risk register.

For trapped-liquid fire rupture studies, retrieve and extract the evidence package before calculation: P&ID isolation boundaries, line lists, piping specs, material certificates, flange/bolt/gasket data, fire-zone/PFP documents, relief basis, and acceptance criteria. Then use neqsim.process.safety.rupture through the neqsim-trapped-liquid-fire-rupture skill and keep missing evidence visible as assumptions/gaps in the report.

For source-document-driven blowdown pipe-fire rupture studies, do not call PipeFireRuptureStudy as a naked solver unless the user explicitly requests a raw screening calculation. Build SafetyEvidenceReference records for source drawings, piping specifications, process/depressurization, material, and fire/PFP inputs; assemble a PipeFireRuptureDataSource; run PipeFireRuptureStudyRunner; and report the returned PipeFireRuptureStudyHandoff. Gate outputs on SafetyStudyReadiness: NOT_READY blocks calculation, SCREENING permits a clearly labelled screening result, and DESIGN_GRADE requires reviewed controlled evidence. When rupture is predicted, carry the pipe_fire_rupture_source_term_handoff.v1 map into consequence analysis.

For source-document-driven dynamic flare and blowdown network studies, do not wire ad hoc transient notebooks directly from extracted tags. Build LineEquipmentListEvidence, PidTopologyEvidence, and DynamicBlowdownFlareStudyDataSource with one BlowdownSource per protected equipment item. Run DynamicBlowdownFlareStudyRunner to execute NeqSim DepressurizationSimulator cases, aggregate simultaneous loads with MultiVesselBlowdownStudy, size PSV orifices where set-pressure evidence is available, and generate dynamic_blowdown_flare_load_handoff.v1 for flare-network, consequence, and report consumers.

Read the full file on GitHub · 365 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. 6d ago First seen · 365 lines · 79 tokens per session scan A 9dcd987523e4

Subscribe to this mod's changes

run neqsim safety and depressuring simulation is an agent published in the GitHub repository equinor/neqsim (150 stars, last pushed today), licensed Apache-2.0. It adds 79 tokens to every session and 3,849 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.