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/usgs-water-mcp-server --skill usgs-water-guidegit clone --depth 1 https://github.com/cyanheads/usgs-water-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/usgs-water-mcp-server/usgs-water-guide)<a href="https://agentmods.dev/skills/cyanheads/usgs-water-mcp-server/usgs-water-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/usgs-water-mcp-server/usgs-water-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/usgs-water-mcp-server/usgs-water-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/usgs-water-mcp-server/usgs-water-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 | $0.00099 | $0.02252 |
| Opus 5.5 | $0.00040 | $0.00901 |
| Sonnet 5.5 | $0.00020 | $0.00450 |
| Haiku 4.5 | $0.00010 | $0.00225 |
Grade A, and why
usgs-water-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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope
Keyless USGS data from continuous sensors at stream gages, lakes, springs, and wells: real-time instantaneous values, daily statistics, site and series metadata, and daily percentiles computed over each site's record.
Not covered:
- Place names and radius search. Geocode elsewhere, then build a
bboxaround the point. - Flood stage, flood categories, forecasts. water_get_conditions ranks a reading against the site's own history only. Pair with a National Weather Service source for flood thresholds.
- Hand-measured well levels and lab water-quality samples. Only wells and sites with a continuous sensor return data here.
Identifiers
| Identifier | Comes from | Goes to |
|---|---|---|
| Site number (8–15 digits, a string with leading zeros; wells are usually 15) | water_find_sites | every site tool |
countyCd (5-digit FIPS) |
expanded water_find_sites rows: stateCd (2-digit FIPS) followed by countyCd (3 digits), e.g. 24 + 047 → 24047; or a FIPS lookup outside this server |
water_find_sites |
stateCd input (2 letters, MD) |
the user | water_find_sites. The output stateCd is the FIPS number and is not accepted back |
huc (2 or 8 digits) |
first 8 digits of a site's hucCd |
water_find_sites |
| Parameter code (5 digits) | water_list_parameters; better, the site's own rows in water_get_site_data_catalog | every data tool |
methodId |
methodId / otherSeries[].methodId in water_get_readings or water_get_series. Daily and instantaneous IDs differ for the same sensor |
water_get_series |
canvas_id + table name |
a truncated water_get_series or water_find_sites response | water_dataframe_describe, water_dataframe_query |
Gates
A listed site is not a live site. water_find_sites has no active-status filter, and hasDataTypeCd: "iv" matches every site that ever reported instantaneous data. Gages whose discharge record ended in 1996 or 2019 come back beside live ones, and dormant sites are often a large share of a result (a majority in some small areas). Before reporting current conditions for an area, keep only sites that produce values:
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 · 88 lines · 99 tokens per session scan A e5275c9c55d2
usgs-water-guide is a skill published in the GitHub repository cyanheads/usgs-water-mcp-server (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 99 tokens to every session and 2,252 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
spatial-video-analysis
Admit explicitly authorized PNG frames and finite spatial scene estimates for the optional pinned Qwen spatial source component. Use for source-only qualification, bounded geometry preparation, source-clock provenance, or diagnosis of its provider refusals and runtime grant block. Do not use this component as proof of…
research-visualization-freecad
Build evidence-grounded FreeCAD research illustrations in an explicitly selected owned local session, and verify saved geometry, viewport images and any bounded FEM result.
research-visualization-blender
Create evidence-grounded Blender research illustrations through an explicitly selected owned local session, then inspect the native scene and resulting images.
internet-archive-guide
Use ia tools to investigate historical web pages or Internet Archive books and documents. Resolve capture and item identities, compare the captures actually served, and check coverage before claiming content absent or fully read.
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…