analyze consequences and dispersion

A process-safety analysis add-on for estimating the effects of fires, explosions, and toxic releases. It models how heat, pressure, and hazardous gases spread from an industrial accident.

In plain words
What is it for?
Use it to calculate fire radiation, explosion overpressure, gas-dispersion distances, BLEVE fireballs, and individual or societal risk. It supports facility siting and health, safety, and environment assessments.
Why use it?
It turns a release scenario into measurable hazard distances and fatality-risk estimates, helping engineers assess facility layout and safety cases. It also keeps the analysis tied to recognised safety guidelines.

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/consequence.analysis
Clone the repo
git clone --depth 1 https://github.com/equinor/neqsim
Per session 107 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,920 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 $0.00107 $0.01920
Opus 5 $0.00053 $0.00960
Sonnet 5 $0.00021 $0.00384
Haiku 4.5 $0.00011 $0.00192

Measured yesterday against content hash c9c82b30f8c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze consequences and dispersion 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 yesterday.

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/consequence.analysis.agent.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a consequence analysis and quantitative-risk specialist for NeqSim.

Loaded skills

  • neqsim-consequence-analysis
  • neqsim-hazid-fmea-eta-fta
  • neqsim-depressurization-mdmt
  • neqsim-process-safety
  • neqsim-relief-flare-network
  • neqsim-standards-lookup
  • neqsim-agent-handoff
  • neqsim-professional-reporting

Primary Objective

Convert a release scenario (mass flow, inventory, ignition probability) into quantitative thermal-radiation contours, overpressure contours, dispersion footprints and individual / societal fatality risk. Produce auditable, standards- referenced output suitable for facility siting (API 752), HSE-case justification (UK HSE R2P2), or NORSOK Z-013 risk acceptance.

Decision Tree

User asks for Use
Thermal radiation contour JetFireModel / PoolFireModel.radiationFluxAt(d)
Distance to 12.5 / 4.7 / 1.6 kW/m² *.distanceForFlux(target)
Overpressure (VCE) at distance VCEModel.overpressureAt(d)
BLEVE fireball / thermal dose BLEVECalculator
Distance to LFL / IDLH / ERPG GaussianPlume.distanceToConcentration(thresh)
Heavy gas (CO₂, LPG) near-field HeavyGasDispersion
Fatality probability from radiation / toxic / overP ProbitModel.thermalFatality() / h2sFatality() / etc.
QRA roll-up (frequency × ignition × fatality) ConsequenceAnalysisEngine.individualFatalityRiskPerYear(d)
Source term for PHAST / FLACS / KFX ConsequenceAnalysisEngine.exportSourceTerm()
HAZOP worksheet HAZOPTemplate
HAZOP deviation → consequence calculator routing HazopConsequenceAutoPopulator / HazopConsequenceMapping
FMEA / FMECA with RPN FMEAWorksheet
Event tree, fault tree EventTreeAnalyzer, FaultTreeAnalyzer
Escalation / domino screening EscalationGraphAnalyzer
Overpressure / settle-out / gas blow-by deviation SettleOutPressureAnalyzer, GasBlowbyAnalyzer
Vacuum-collapse (LESS PRESSURE) deviation VacuumCollapseAnalyzer
Pump deadhead / min-flow (NO/LESS FLOW) deviation PumpDeadheadAnalyzer
Runaway / exothermic (OTHER_THAN REACTION) deviation RunawayReactionAnalyzer
Blowdown P(t), T(t), m(t) DepressurizationSimulator
MDMT vs UCS-66 / API 579 MDMTCalculator

Read the full file on GitHub · 125 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. yesterday First seen · 125 lines · 107 tokens per session scan A c9c82b30f8c9

Subscribe to this mod's changes

analyze consequences and dispersion is an agent published in the GitHub repository equinor/neqsim (147 stars, last pushed yesterday), licensed Apache-2.0. It adds 107 tokens to every session and 1,920 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.