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 SteadfastAsArt/geoscience-skills --skill rockhoundgit clone --depth 1 https://github.com/SteadfastAsArt/geoscience-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/steadfastasart/geoscience-skills/rockhound)<a href="https://agentmods.dev/skills/steadfastasart/geoscience-skills/rockhound"><img src="https://agentmods.dev/badge/skills/steadfastasart/geoscience-skills/rockhound/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/steadfastasart/geoscience-skills/rockhound"><img src="https://agentmods.dev/badge/skills/steadfastasart/geoscience-skills/rockhound.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 | $0.00047 | $0.00712 |
| Opus 5.5 | $0.00019 | $0.00285 |
| Sonnet 5.5 | $0.00009 | $0.00142 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
rockhound 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 1mo 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RockHound maintenance and migration
RockHound's repository was archived in 2022 and recommends Ensaio. Preserve a working legacy environment while assessing supported replacements; there is no universal one-to-one mapping of fetcher names or return objects.
Inspect an existing workflow
Identify the exact fetcher, data version, source URL/hash, cache location, parser
and scientific conventions. Set ROCKHOUND_DATA_DIR before importing RockHound
if a separate cache is needed. Never delete a user's cache to test a migration.
Legacy PREM load
This fragment uses the upstream registry and may download from EarthScope/IRIS. It loads the 1 s PREM radial Earth model, not a local field observation. The registry URL returned HTTP 404 during the 2026-09-14 check. This example currently needs an existing hash-verified cache or a separately verified source; it is not a successful fresh-download recipe. The test suite exercises the real loader with a clearly synthetic cache fixture, without claiming PREM validation.
# example: legacy-prem
import rockhound
prem = rockhound.fetch_prem()
radius_km = prem["radius"].to_numpy()
depth_km = prem["depth"].to_numpy()
density_g_cm3 = prem["density"].to_numpy()
vpv_km_s = prem["Vpv"].to_numpy()
vsv_km_s = prem["Vsv"].to_numpy()
The table contains discontinuities and distinct vertical/horizontal velocities. Preserve repeated boundary radii and choose a side explicitly for interpolation. Zero shear velocity in a fluid region is meaningful, not a missing value. Do not send the full radial model directly to a plane-layer surface-wave solver.
Migration steps
- Find a maintained dataset release, its redistribution license and immutable identifier. If Ensaio has no matching dataset, use a documented Pooch registry and the original provider instead of substituting unrelated sample data.
- Compare downloaded hashes or document changed releases; inspect units, grid registration, coordinates, missingness and source preprocessing.
- Adapt the return contract: an Ensaio path still needs a CSV/NetCDF reader, while RockHound may return a DataFrame or xarray object.
- Verify representative values and downstream results before replacing imports. Diagnose failed old URLs; do not bypass TLS or checksum checks.
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.
- 1mo ago First seen · 68 lines · 47 tokens per session scan A 0ce78b7ce8c4
rockhound is a skill published in the GitHub repository SteadfastAsArt/geoscience-skills (70 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 712 once invoked, about $0.0002 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 2026-09-16.
Other skills, from other repositories
glm-lake-mendota
Simulate vertical water temperature profiles for lakes using the General Lake Model (GLM), calibrate key parameters to minimize RMSE against field observations, and produce validated NetCDF output.
obspy-seismology
Seismological data analysis with ObsPy — FDSN waveform download, response removal, phase picking, moment tensor inversion, and seismicity mapping.
xarray-netcdf
Labeled multi-dimensional array analysis with xarray: NetCDF/HDF5 I/O, lazy Dask loading, rechunking, Zarr stores, and CF conventions.
soil-data
Soil data analysis via SoilGrids 2.0 REST API and SSURGO: SOC stocks, texture classification, kriging interpolation, and soil profile visualization.
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…