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 reesehammer/umbra-py --skill umbra-sargit clone --depth 1 https://github.com/reesehammer/umbra-pyWrote 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/reesehammer/umbra-py/umbra-sar)<a href="https://agentmods.dev/skills/reesehammer/umbra-py/umbra-sar"><img src="https://agentmods.dev/badge/skills/reesehammer/umbra-py/umbra-sar/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/reesehammer/umbra-py/umbra-sar"><img src="https://agentmods.dev/badge/skills/reesehammer/umbra-py/umbra-sar.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 | $0.00066 | $0.00582 |
| Opus 5.5 | $0.00026 | $0.00233 |
| Sonnet 5.5 | $0.00013 | $0.00116 |
| Haiku 4.5 | $0.00007 | $0.00058 |
Grade A, and why
umbra-sar 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 8d 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.
What it actually says
Umbra open SAR
Use this when the user asks for SAR, radar, Umbra, or imagery of a place that should not depend on daylight or clear skies.
Search
Call search_catalog with a place or a bbox, optional start and end,
limit of 20 or less, and canonical true. Report how many cards came back
and the newest datetime on them. The open archive can lag weeks behind
Umbra's newest collects, so always state the newest date you found and never
say "latest" without it.
Map
Turn each card's bbox into a GeoJSON polygon. bbox is
[west, south, east, north]. Assemble one FeatureCollection and set
properties id, datetime, platform, resolution, and polarizations.
Add that collection with the host map's GeoJSON tool, then fit the extent.
Preview
Call quicklook with url set to the card's stac_href. The picture is a
512 px baked preview. Do not describe detail finer than that image shows.
Open pixels
Call get_item on the chosen stac_href, then take the GEC product url.
That file is a cloud-optimized GeoTIFF on Umbra's public bucket. The bucket
allows cross-origin GET with Range requests, so a map's COG layer may be able
to stream it directly. This is not verified for every reader, and if it fails,
fall back to the quicklook plus a local download.
For a copy on disk, use the client's own downloader. On the hosted server,
download_asset is a size check only: pass confirm false and read bytes.
Do not pass confirm true there.
Honesty
A GEC is detected amplitude, already map-projected. SICD and CPHD are complex products for the user's own tools. umbra-py does not form images, do InSAR, or preserve phase. Never difference HH against VV. Always carry this line: Contains Umbra open data, licensed under CC BY 4.0.
Limits
The hosted host allows 120 requests per minute. A refused tool (a composite,
a stack, or narration) means run a local server:
uvx --from 'umbra-py[mcp]' umbra-mcp.
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.
- 8d ago First seen · 57 lines · 66 tokens per session scan A 55cba2411a0e
umbra-sar is a skill published in the GitHub repository reesehammer/umbra-py (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 66 tokens to every session and 582 once invoked, about $0.0003 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 2026-10-17.
Other skills, from other repositories
cheminformatics
Molecular structure analysis, SAR triage, compound library characterization, QSAR modeling, ADMET prediction, chemical space visualization, target engagement assessment, drug perturbation connectivity scoring, and selectivity profiling.
phidown
Search, filter, download, and analyze Copernicus Data Space products with the phidown project. Use this skill when a user asks to find Sentinel products, query by AOI/date/product type, run burst coverage analysis, download by product name or S3 path, configure credentials (.s5cfg), troubleshoot phidown CLI/Python…
chembl-bioactivity
Use this Skill to query ChEMBL for bioactivity data: target lookup, IC50/Ki retrieval, activity cliffs, SAR tables, and pChEMBL-normalized values.
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…
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
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…