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-sodir-open-datagit 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-sodir-open-data)<a href="https://agentmods.dev/skills/equinor/neqsim-community-skills/neqsim-sodir-open-data"><img src="https://agentmods.dev/badge/skills/equinor/neqsim-community-skills/neqsim-sodir-open-data/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-sodir-open-data"><img src="https://agentmods.dev/badge/skills/equinor/neqsim-community-skills/neqsim-sodir-open-data.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 | $0.00107 | $0.03170 |
| Opus 5.5 | $0.00043 | $0.01268 |
| Sonnet 5.5 | $0.00021 | $0.00634 |
| Haiku 4.5 | $0.00011 | $0.00317 |
Grade A, and why
neqsim-sodir-open-data 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 10d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sodir Open Data (Sokkeldirektoratet)
Sodir publishes its petroleum, CO2, seabed-mineral and survey data openly under NLOD 2.0 (reuse with attribution). This skill is the single place agents learn what exists, which layer answers which question, how to read it, and the traps. Page of record: https://www.sodir.no/fakta/data-og-analyser/apne-data/ (it answers HTTP 403 to scripts - use the service hosts below, never scrape it).
When to Use
- A task needs an official NCS fact: well, DST, formation top, field reserves, production history, owner or operator, licence, facility, pipeline, survey or CO2 storage record.
- You must pick the right Sodir layer or table, or need a prior for a fluid or reservoir model when no PVT study exists.
- A company data source (GeoX, PDM, SMDA) is unavailable and Sodir is the open cross-check.
Inputs
Field, discovery, well or licence name (or NPDID), an optional bounding box (WGS84), the question to answer,
and the data tier required (screening only: open data never replaces PVT or governed data).
Outputs
Rows (dict per record) with the layer id, join keys and retrieval date; provenance() source list for
results.json / SOURCES.md; assumptions and data_gaps for anything not open.
Engineering Method
- Identify the question with
search()/use_case()and the layer table below. - Query server-side (
where,bbox,out_fields) and join on*Npdid*keys, not names. - Convert dates (Europe/Oslo) and geometry (
out_sr=4326), take the latest version/valid-to-null rows. - Label every derived number
screening, cite Sodir (NLOD 2.0) and record the gaps.
Routes (all keyless GET)
| Route | URL | Use |
|---|---|---|
| DataService REST (preferred) | https://factmaps.sodir.no/api/rest/services/DataService/Data/MapServer/{id}/query |
Every FactPages table and layer, SQL where, paging, bbox, JSON |
| DataService metadata | .../DataService/Metadata/MapServer/10 (tables), /11 (attributes) |
Table and column descriptions |
| FactPages CSV views | https://factpages.sodir.no/public?/Factpages/external/tableview/{view}&rs:Format=CSV... |
Whole table as CSV (field_production_monthly, field_reserves, wellbore_exploration_all, wellbore_development_all, wellbore_formation_top, licence_licensee_hst, ...) |
| FactMaps map services | .../Factmaps/FactMapsWGS84/MapServer and FactMapsED50UTM32 |
Styled map layers, WMS/WFS/OGC, GetCapabilities |
| Bulk files | https://factpages.sodir.no/downloads/{shape|csv}/{name}.zip, FGDB SODIR_FactMaps_data_v3_0.zip |
GIS/offline (CSV has WKT geometry; only FGDB is complete) |
| Themes | .../Themes/CO2_storage_{depths,options,thickness}_1_0/MapServer |
CO2 storage atlas |
| Human viewers | factmaps.sodir.no/map, survey map, Deep Sea Surveys, CO2 atlas | Look, do not script |
| geonorge.no | national catalogue copy | Alternative discovery |
What ships with it
11 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.
- pyproject.toml 773 B
- README.md 387 B
- src/sodir_open_data/__init__.py 643 B runs code
- src/sodir_open_data/__main__.py 1.8 KB runs code
- src/sodir_open_data/catalog.py 4.0 KB runs code
- src/sodir_open_data/client.py 8.9 KB runs code
- src/sodir_open_data/data/dataservice_catalog.json 203 KB
- src/sodir_open_data/downloads.py 5.4 KB runs code
- src/sodir_open_data/guides.py 9.0 KB runs code
- src/sodir_open_data/refresh.py 3.6 KB runs code
- tests/test_sodir_open_data.py 4.4 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.
- 10d ago Changed · +11 lines 9b2ec24c819a
- 11d ago First seen · 153 lines · 107 tokens per session scan A c1ec8ac8a83b
neqsim-sodir-open-data is a skill published in the GitHub repository equinor/neqsim-community-skills (4 stars, last pushed today), licensed Apache-2.0. It adds 107 tokens to every session and 3,170 once invoked, about $0.0004 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 2026-10-26.
neqsim-sodir-open-data compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| neqsim-sodir-open-dataequinor/neqsim-community-skills | Skill | 4 | today | Apache-2.0 | A | 107 | 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 |