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 skills add equinor/neqsim-community-skills --skill neqsim-ncs-infrastructure-networkgit clone --depth 1 https://github.com/equinor/neqsim-community-skillsWrote 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/skills/equinor/neqsim-community-skills/neqsim-ncs-infrastructure-network)<a href="https://agentmods.dev/skills/equinor/neqsim-community-skills/neqsim-ncs-infrastructure-network"><img src="https://agentmods.dev/badge/skills/equinor/neqsim-community-skills/neqsim-ncs-infrastructure-network/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/skills/equinor/neqsim-community-skills/neqsim-ncs-infrastructure-network"><img src="https://agentmods.dev/badge/skills/equinor/neqsim-community-skills/neqsim-ncs-infrastructure-network.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 | $0.00117 | $0.04124 |
| Opus 5.5 | $0.00047 | $0.01650 |
| Sonnet 5.5 | $0.00023 | $0.00825 |
| Haiku 4.5 | $0.00012 | $0.00412 |
Grade A, and why
neqsim-ncs-infrastructure-network scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Open-API clients take an injectable `fetch(url, timeout) -> bytes`, which How it starts
The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NCS Infrastructure Network
This skill gives an agent a working model of how the Norwegian Continental Shelf (NCS) is connected. It covers the physical chain from each field through host platforms and trunklines to the onshore processing plants, the receiving terminals in the UK and continental Europe, and the markets. The graph is built from open data only:
| Source | What it provides | Access |
|---|---|---|
| Sodir DataService (ArcGIS REST) | fields, discoveries, facilities, pipelines, reserves, yearly profiles, field "Transport" descriptions | open API, NLOD 2.0 |
| Sodir FactPages CSV | the same tables as flat CSV | open API |
| norskpetroleum.no | pipeline capacity tables (gas MSm3/d, oil Sm3/d) | open download |
| gassco.eu plant pages | Kollsnes, Nyhamna capacities; Kårstø product rates; terminal list | open web |
| ENTSOG Transparency | daily physical flow at every Norwegian entry point | open API |
A bundled snapshot (data/ncs_network_snapshot.json) makes the skill work
offline. scripts/build_snapshot.py rebuilds it from the live APIs in a minute.
It is a screening model of connectivity and nameplate capacity. It is not a
hydraulic model of Gassled, not the Gassco nomination system, and not a booking
tool. Hydraulic checks are handed to NeqSim LoopedPipeNetwork.
When to Use
- A task asks where a field's gas or oil goes, and through which pipelines, plants and terminals.
- A task needs the fields that share a trunkline, plant or terminal, e.g. before a tie-in, a shutdown or a capacity study.
- A task needs trunkline and plant utilisation for a historical year, or for
forecast rates from
neqsim-ncs-value-chain-optimization. - A task asks what an outage of a pipeline, riser platform or plant strands or reroutes, or which elements are single points of failure.
- A discovery needs its nearest in-service processing hosts and a NeqSim
TiebackAnalyzerscreening against them. - A study needs live open data: Sodir tables through
SodirDataService/SodirFactPages, or observed terminal entry flows from ENTSOG to calibrate the model.
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/ncs_network_walkthrough.py 1.9 KB runs code
- pyproject.toml 804 B
- README.md 2.0 KB
- scripts/build_snapshot.py 2.0 KB runs code
- src/ncs_infrastructure_network/__init__.py 946 B runs code
- src/ncs_infrastructure_network/build.py 17 KB runs code
- src/ncs_infrastructure_network/data/ncs_network_snapshot.json 1164 KB
- src/ncs_infrastructure_network/neqsim_bridge.py 12 KB runs code
- src/ncs_infrastructure_network/network.py 17 KB runs code
- src/ncs_infrastructure_network/open_api.py 13 KB runs code
- src/ncs_infrastructure_network/sources.py 6.0 KB runs code
- src/ncs_infrastructure_network/topology.py 15 KB runs code
- src/ncs_infrastructure_network/transport_parser.py 6.5 KB runs code
- tests/test_network_snapshot.py 2.9 KB runs code
- tests/test_open_api_parser_build.py 6.1 KB runs code
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.
- 7d ago Changed · +2 lines 69bba517c06a
- 10d ago Changed · +9 lines 8595be176195
- 11d ago Changed · +3 lines 4c47f354a17d
- 18d ago Changed · +16 lines 90f390a9ddb1
- 27d ago Changed · +24 lines ed4c134e1b44
- 1mo ago Changed · +2 lines 9b907d404c7c
- 1mo ago First seen · 228 lines · 117 tokens per session scan A 670c8f259f06
neqsim-ncs-infrastructure-network is a skill published in the GitHub repository equinor/neqsim-community-skills (4 stars, last pushed today), licensed Apache-2.0. It adds 117 tokens to every session and 4,124 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-27.
neqsim-ncs-infrastructure-network compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| neqsim-ncs-infrastructure-networkequinor/neqsim-community-skills | Skill | 4 | today | Apache-2.0 | A | 117 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 3d ago | Apache-2.0 | A | 123 | Claude Code |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 83 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 44 | Claude Code |
| phylogeneticsK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 71 | Claude Code, Codex |
| research-engineerdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 43 | Claude Code, Codex |
| mapping-to-snomedmaziyarpanahi/openmed | Skill | 5.8k | yesterday | Apache-2.0 | A | 205 | Claude Code |