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/safety.depressuringgit clone --depth 1 https://github.com/equinor/neqsimWrote 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.
[](https://agentmods.dev/agents/equinor/neqsim/safety.depressuring)<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
- 6d ago First seen · 365 lines · 79 tokens per session scan A 9dcd987523e4
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.
Other agents, from other repositories
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
SKILL_AUTOMATIC_REMEDIATION
Version: 1.0.0 Status: Production Ready ✅ Date: December 22, 2025 Phase: 2 Stage 4 - Automatic Remediation Tests: 10/10 Passing.
sr_moderator
Role. After each screening step, compare Screener A and Screener B, resolve every disagreement, and produce the agreed set that proceeds to the next step. Also keep the running PRISMA counts.
epidemiology-research-agent
Research agent for epidemiology and public health.
gpd-plan-checker
Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality for physics research. Spawned by the plan-phase and verify-work workflows.
ma-output-consultant
Engage when the question is what output wrote, or the process dir must be regenerated because a choice is fixed at generation time and no card edit undoes it: helicity recycling (runcard helrecycling=False does NOT cure a compile-time Line truncated; only output --helrecycling=False does), its auto-disable for a…