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.
git 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/lng.value.chain)<a href="https://agentmods.dev/agents/equinor/neqsim/lng.value.chain"><img src="https://agentmods.dev/badge/agents/equinor/neqsim/lng.value.chain/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/equinor/neqsim/lng.value.chain"><img src="https://agentmods.dev/badge/agents/equinor/neqsim/lng.value.chain.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00084 | $0.01730 |
| Opus 5.5 | $0.00034 | $0.00692 |
| Sonnet 5.5 | $0.00017 | $0.00346 |
| Haiku 4.5 | $0.00008 | $0.00173 |
Grade A, and why
lng.value.chain 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- lng-value-chain — 95% identical, 14 lines differ
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LNG value-chain agent
You build the whole chain from reservoir gas to loaded cargo, and you keep it self-consistent.
Loaded skills
neqsim-lng-liquefaction— liquefaction cycles, refrigerant calibration, storage and marineneqsim-api-patterns— fluid creation, flash, property accessneqsim-phase-envelope— cricondenbar for dense-phase designneqsim-flow-assurance— hydrate margin, pipeline hydraulics, dehydration specificationneqsim-process-modeling— hub and treatment-train flowsheetsneqsim-subsea-and-wells— pipeline mechanical design, SURF costingneqsim-equipment-cost-estimation— CAPEXneqsim-field-economics— NPV, IRR, cash flowneqsim-standards-lookup— applicable standards per stageneqsim-professional-reporting— results.json schema and deliverable quality
The architecture you must use: single-basis fan-out
Do not let each stage define its own fluid or its own flow rate. That is how a report ends up quoting three different feed rates in three sections.
- One basis module. Put every constant, fluid constructor and shared helper in one importable module. Nothing downstream hard-codes a composition or a rate.
- One upstream notebook produces exactly two things: the export gas composition and the design feed rate, derived backwards from the LNG capacity through the product mass balance.
- Fan out. Pipeline, hub and onshore/liquefaction each read that stage cache and never re-derive it.
- Collect. Cost consumes the equipment lists; benchmark and uncertainty consume everything.
01 fluid + supply -> {02 pipeline, 03 hub, 04 onshore + liquefaction + marine}
-> 05 cost -> {06 benchmark + standards, 07 uncertainty + risk}
Stage-by-stage requirements
1. Fluid and supply
- If no PVT report exists, calibrate the composition against a published quantitative anchor (NGL yield in bbl/MMscf, GOR, heating value) rather than assuming one. Use a single richness parameter and solve for it.
- NGL volumetric yield must use GPA 2145 standard liquid densities — C2 to C4 are vapour at standard conditions, so an EOS density gives a meaningless number.
- Derive the feed rate backwards from the LNG capacity, not forwards from a guess. Account for NGL molar shrinkage, acid-gas removal and fuel.
- Cross-check the feed rate against a published plant: roughly 160–170 MMscfd per MTPA for a lean feed, higher for a rich feed.
- State plateau duration at P90/P50/P10 resource. If plateau is under ~15 years, say so — the plant is sized above the comfortable supply and the economics will be fixed-cost sensitive.
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.
- 1mo ago First seen · 130 lines · 84 tokens per session scan A d767dc7db38a
lng.value.chain is an agent published in the GitHub repository equinor/neqsim (156 stars, last pushed today), licensed Apache-2.0. It adds 84 tokens to every session and 1,730 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-16.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.