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-weather-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-weather-data)<a href="https://agentmods.dev/skills/equinor/neqsim-community-skills/neqsim-weather-data"><img src="https://agentmods.dev/badge/skills/equinor/neqsim-community-skills/neqsim-weather-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-weather-data"><img src="https://agentmods.dev/badge/skills/equinor/neqsim-community-skills/neqsim-weather-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 | $0.00104 | $0.03354 |
| Opus 5.5 | $0.00042 | $0.01342 |
| Sonnet 5.5 | $0.00021 | $0.00671 |
| Haiku 4.5 | $0.00010 | $0.00335 |
Grade A, and why
neqsim-weather-data 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 19d 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.
- Every HTTP client takes an injectable `fetch(url, timeout) -> bytes`, which How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Weather Data for Installations
This skill gives an agent live and historical weather, wind and sea-state data for any installation, onshore or offshore, from open APIs that need no account, subscription or API key:
| Source | What it provides | Coverage | Access |
|---|---|---|---|
| Open-Meteo Forecast API | hourly temperature, humidity, pressure, wind, cloud cover, precipitation | worldwide, up to 16 days ahead | open, keyless |
| Open-Meteo Historical Weather API | the same variables from ERA5/ERA5-Land/IFS reanalysis | worldwide, 1940 to present | open, keyless |
| Open-Meteo Marine Weather API | wave height/period/direction, swell, sea-surface temperature | worldwide coastal/offshore | open, keyless |
| Open-Meteo Geocoding API | place/installation name to coordinates | worldwide | open, keyless |
| MET Norway Locationforecast | hourly forecast from the MET Nordic model (~1 km) | Norway/Sweden/Denmark, ~9 days ahead | open, requires a descriptive User-Agent header only |
Sodir DataService facility layer |
installation name to WGS84 position (best-effort) | Norwegian Continental Shelf | open API, NLOD 2.0 |
It is built especially to work well on the Norwegian Continental Shelf (MET Norway's 1 km Nordic model plus the Sodir facility register let an agent resolve "Troll A" or "Åsgard B" by name and cross-check two independent forecast sources), while every function also works anywhere in the world given a name (Open-Meteo geocoding) or a latitude/longitude.
It is a data-retrieval skill: it returns measured/modelled weather series and simple empirical summaries, not a certified met-ocean design study. Design wind, wave and temperature return periods, extreme-value (Gumbel/Weibull) statistics and site-specific met-ocean criteria require a qualified met-ocean study; this skill only gives a screening-level, order-of-magnitude picture to scope one.
When to Use
- A task needs the current or forecast ambient temperature, wind speed/ direction/gust, humidity or pressure at an installation, by name or by coordinates.
- A task needs historical weather ("what has the weather been like here") for a past incident window, a fouling/corrosion season, or a design-basis screening statistic (min/mean/max temperature, wind speed percentile).
- A task needs a forward-looking forecast (hours to ~16 days) to plan a lift, a flaring event, a marine operation, or a fire-water/dispersion screening.
- A task needs wave height, wave period or sea-surface temperature for an offshore installation or subsea cooldown screening.
- An agent needs a Pasquill-Gifford stability class for
neqsim-gas-dispersion-distance-screeningfrom live wind speed, time of day and cloud cover, instead of an assumed class. - An agent needs ambient temperature and elevation for
neqsim-gas-turbine-performance-screening, or a wind speed forneqsim-firewater-deluge-design's monitor/wind-drift screening, without the user supplying them by hand. - A root-cause or operational investigation needs the weather at an
equipment's location for a past trip/anomaly window, to test whether an
ambient-temperature, wind, or sea-state condition was a candidate driver
(feeds
neqsim-root-cause-analysis's "Weather as Evidence" method andneqsim-autonomous-investigation's lead-lag relationship discovery).
What ships with it
14 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/weather_data_walkthrough.py 2.3 KB runs code
- pyproject.toml 606 B
- README.md 507 B
- src/weather_data/__init__.py 1.1 KB runs code
- src/weather_data/metno.py 4.7 KB runs code
- src/weather_data/ncs_facilities.py 4.6 KB runs code
- src/weather_data/open_meteo.py 8.5 KB runs code
- src/weather_data/service.py 8.0 KB runs code
- src/weather_data/site_conditions.py 5.9 KB runs code
- tests/test_metno.py 3.9 KB runs code
- tests/test_ncs_facilities.py 2.0 KB runs code
- tests/test_open_meteo.py 5.2 KB runs code
- tests/test_service.py 5.9 KB runs code
- tests/test_site_conditions.py 3.0 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.
- 19d ago Changed 33b3ff01d70f
- 1mo ago First seen · 244 lines · 104 tokens per session scan A 6c09605f80c7
neqsim-weather-data is a skill published in the GitHub repository equinor/neqsim-community-skills (4 stars, last pushed today), licensed Apache-2.0. It adds 104 tokens to every session and 3,354 once invoked, about $0.0004 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 2026-10-02.
neqsim-weather-data compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| neqsim-weather-dataequinor/neqsim-community-skills | Skill | 4 | today | Apache-2.0 | A | 104 | 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 |