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-marine-mcp-server --skill noaa-marine-guidegit clone --depth 1 https://github.com/cyanheads/noaa-marine-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-marine-mcp-server/noaa-marine-guide)<a href="https://agentmods.dev/skills/cyanheads/noaa-marine-mcp-server/noaa-marine-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/noaa-marine-mcp-server/noaa-marine-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-marine-mcp-server/noaa-marine-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/noaa-marine-mcp-server/noaa-marine-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 | $0.00106 | $0.01960 |
| Opus 5.5 | $0.00042 | $0.00784 |
| Sonnet 5.5 | $0.00021 | $0.00392 |
| Haiku 4.5 | $0.00011 | $0.00196 |
Grade A, and why
noaa-marine-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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope
Keyless. CO-OPS covers US coasts, territories, and the Great Lakes: tide and tidal-current predictions, observed water levels, and verified monthly means. NDBC serves the newest observation from a buoy or fixed station: surface weather and waves, an ADCP current profile, or water-column sensors.
Reach elsewhere for:
- Forecasts of any kind (wind, waves, swell, weather) and marine warnings or advisories. Use a National Weather Service server for marine zone forecasts and alerts, and a marine wave-forecast server for swell at a coordinate.
- Past buoy readings. The NDBC tools return only the newest observation, so they can't show yesterday's swell or a trend over the last few hours.
- Geocoding. Station search matches station names and IDs, not places.
Identifiers
| ID shape | Source | Read by |
|---|---|---|
Numeric, e.g. 9447130 |
CO-OPS tide or water-level station | capabilities decides: tide → tide predictions; water_level → water level and monthly means |
Alphanumeric, e.g. PUG1515, plus a bin number |
CO-OPS current station | noaa_marine_get_currents, with bin taken from that station's bins[] |
Mostly 5 characters, e.g. 46041, FRDW1; some are 7-digit numbers |
NDBC station | capabilities decides: met → conditions; current_profile → current profile; water_quality → ocean observations |
- NDBC relays many CO-OPS gauges under its own ID, and the NDBC station's name starts with the CO-OPS number:
FRDW1is named9449880 - Friday Harbor, WA. Aqueryfor a CO-OPS number therefore returns the CO-OPS row first, followed by any NDBC relay. When the gauge also reports wind and air data,noaa_marine_get_conditionsreads either ID: the CO-OPS number resolves to the relay, returning the relay asstation_idand the CO-OPS number ascoops_station_id. Every other NDBC tool takes the NDBC ID only. - A tide station is not necessarily a gauge. Most tide-prediction stations are prediction-only, and only those whose
capabilitiesincludewater_levelhave observations.
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 Changed bc6f5f021f79
- yesterday First seen · 64 lines · 106 tokens per session scan A a8eabb49313b
noaa-marine-guide is a skill published in the GitHub repository cyanheads/noaa-marine-mcp-server (1 stars, last pushed today), licensed Apache-2.0. It adds 106 tokens to every session and 1,960 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 2026-10-28.
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-spaceweather-guide
Judgment for the noaaspaceweather tools — turning SWPC Kp, storm scales, solar wind, flares, and alerts into answers about aurora visibility tonight, coming geomagnetic storms, radio blackouts, and impacts on HF radio, GPS, satellites, and power grids. Use before answering an aurora or space-weather question with…
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).