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 cyanheads/noaa-spaceweather-mcp-server --skill noaa-spaceweather-guidegit clone --depth 1 https://github.com/cyanheads/noaa-spaceweather-mcp-serverWrote 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/cyanheads/noaa-spaceweather-mcp-server/noaa-spaceweather-guide)<a href="https://agentmods.dev/skills/cyanheads/noaa-spaceweather-mcp-server/noaa-spaceweather-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/noaa-spaceweather-mcp-server/noaa-spaceweather-guide/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/cyanheads/noaa-spaceweather-mcp-server/noaa-spaceweather-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/noaa-spaceweather-mcp-server/noaa-spaceweather-guide.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 | $0.00101 | $0.02542 |
| Opus 5.5 | $0.00040 | $0.01017 |
| Sonnet 5.5 | $0.00020 | $0.00508 |
| Haiku 4.5 | $0.00010 | $0.00254 |
Grade A, and why
noaa-spaceweather-guide 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 today.
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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope
The server reads NOAA SWPC's live public feeds: storm scales, planetary Kp, the OVATION aurora nowcast, L1 solar wind, GOES X-ray and proton flux, flare events, active regions, the forecast discussion, and alert products. Keyless.
The feeds reach only a short way back and ahead:
| Data | Reaches back | Reaches ahead |
|---|---|---|
| Kp observed / forecast, storm-scale forecast | 7 days (Kp) | 3 UTC days, starting today |
| Aurora (OVATION) | now only | 30–90 min, the solar wind's L1-to-Earth travel time (forecastTime) |
| Solar wind | ~24 h | none — it is measured upstream of Earth |
| Flare events | 7 days | flare-class probabilities, 3 days |
| Alerts | roughly the last 30 days | Watches list up to 3 UTC days |
A storm older than the feed's reach, or "this week" beyond day 3, is out of reach: say so rather than extrapolating. There is no CME arrival model, no TEC or GPS-error product, and no HF absorption map; the forecast discussion and Watch comments are the only statements of cause and arrival.
Seeing aurora also needs a clear, dark sky. Cloud cover and moonlight are not here; pair with a weather server for clouds and an astronomy server for the moon.
Identifiers
- Geomagnetic latitude comes from
noaa_spaceweather_get_aurora_forecastcalled with coordinates (geomagneticLatitude,minKpRequired). Every "aurora to ~N°" figure on the Kp and conditions tools is geomagnetic, and geographic latitude can differ by up to ~9° either way: Seattle (47.6°N) is 53.0° geomagnetic, London (51.5°N) 53.4°, Yakutsk (62.0°N) 53.4°. Never compare a geographic latitude against those figures; look the place up. - Alert serials link records. A message's
Continuation of Serial Number,Cancel Serial Number, orExtension to Serial Numberline names another record'sserialNumberunder the samemessageCode. Records joined by continuation lines are one ongoing event: count and report it once, using the newest record. A serial can repeat: aCORRECTEDrecord reuses the serial of the one it replaces, so take the newest by issue time. - Flare source. Flare events carry no region. A ≥M5 flare's
SUMXM5summary alert states its diskLocation(for example N08W50); below M5, use the per-region C/M/X counts onnoaa_spaceweather_get_solar_activity.
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.
- today First seen · 73 lines · 101 tokens per session scan A a11f14b7eaee
noaa-spaceweather-guide is a skill published in the GitHub repository cyanheads/noaa-spaceweather-mcp-server (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 101 tokens to every session and 2,542 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 2026-10-30.
Other skills, from other repositories
open-meteo-guide
Tool choice, gates, and workflows for the openmeteo weather tools, covering threshold odds from the ensemble, frost, anomalies against a normal, 2050 projections, surf spots, river flood outlooks, and air quality for a set hour. Use before answering a weather, climate, marine, river, or air-quality question from…
ensembl-guide
Gates and identifier chains for the ensembl tools. Covers checking a coordinate's assembly before you pass it in, finding a gene's counterpart in another species through homology, reading multi-allelic and capped VEP results, and which Ensembl object holds the UniProt, RefSeq, GO, and PDB references. Use when an…
noaa-marine-guide
Gates and conventions for the noaamarine tools (NOAA CO-OPS tides, tidal currents, water levels; NDBC buoys). Covers which station serves which tool, why a place-name search misses, time-zone and direction conventions across the two sources, and what the server cannot answer (forecasts, warnings, past buoy readings).…
usgs-water-guide
Gates and workflows for the water tools over USGS stream gages and groundwater wells. Covers whether a river or aquifer is high or low right now, telling live gages from discontinued ones, reading depth-to-water rankings (they run inverted), finding the parameter code a site actually reports, time zones and data lag…
openfoodfacts-guide
Judgment for the off tools (Open Food Facts) — allergy checks that never overclaim, choosing among a product's many barcodes, where tag IDs come from, grade ranges, free-from searches, and the search budget. Use when answering allergy, diet, ingredient, additive, Nutri-Score, NOVA, or product-comparison questions…
omh-geospatial-analysis
This is an OMH geospatial-analysis workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).