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 opengeos/geoai-skills --skill search-stacgit clone --depth 1 https://github.com/opengeos/geoai-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/opengeos/geoai-skills/search-stac)<a href="https://agentmods.dev/skills/opengeos/geoai-skills/search-stac"><img src="https://agentmods.dev/badge/skills/opengeos/geoai-skills/search-stac/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/opengeos/geoai-skills/search-stac"><img src="https://agentmods.dev/badge/skills/opengeos/geoai-skills/search-stac.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 | $0.00034 | $0.00937 |
| Opus 5 | $0.00017 | $0.00468 |
| Sonnet 5 | $0.00007 | $0.00187 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
search-stac 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 12d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are helping the user search and download satellite imagery from the Planetary Computer STAC catalog using geoai.
Input: $@
Follow these steps in order.
Step 1 -- Determine the action
Parse $@ to identify what the user wants:
- If the input is
list,collections, or asks "what is available": list collections. - If a collection name and
--bboxare provided: search for items. - If
--downloadis present: download items after searching.
Step 2 -- List collections (if requested)
python3 -c "
import geoai
df = geoai.pc_collection_list()
print(df.to_string())
"
If the user provided a filter keyword, pass it:
python3 -c "
import geoai
df = geoai.pc_collection_list(filter_by='FILTER')
print(df.to_string())
"
Report the available collections and stop (unless the user also specified a search).
Step 3 -- Search for items
Parse the collection name, bounding box (--bbox), and optional datetime range (--datetime).
The datetime range should be in the format YYYY-MM-DD/YYYY-MM-DD (start/end).
python3 -c "
import geoai
items = geoai.pc_stac_search(
collection='COLLECTION',
bbox=[MINX, MINY, MAXX, MAXY],
time_range='TIME_RANGE',
limit=LIMIT,
)
print(f'Found {len(items)} items')
print('---')
for item in items[:20]:
assets = list(item.assets.keys())
print(f' {item.id}: {item.datetime} - assets: {assets}')
"
Replace COLLECTION, MINX, MINY, MAXX, MAXY, TIME_RANGE, and LIMIT with actual values. Use limit=10 by default.
If time_range was not specified, omit it or pass None.
Step 4 -- List assets for an item (optional)
If the user asks about available assets or bands for a specific item:
python3 -c "
import geoai
assets = geoai.pc_item_asset_list(item_id='ITEM_ID', collection='COLLECTION')
for name, info in assets.items():
print(f' {name}: {info}')
"
Step 5 -- Download items (if --download flag or user confirms)
python3 -c "
import geoai, os
items = geoai.pc_stac_search(
collection='COLLECTION',
bbox=[MINX, MINY, MAXX, MAXY],
time_range='TIME_RANGE',
limit=LIMIT,
)
output_dir = 'OUTPUT_DIR'
os.makedirs(output_dir, exist_ok=True)
result = geoai.pc_stac_download(
items,
output_dir=output_dir,
)
print(f'Downloaded to: {output_dir}')
for f in os.listdir(output_dir):
fpath = os.path.join(output_dir, f)
if os.path.isfile(fpath):
size_mb = os.path.getsize(fpath) / (1024 * 1024)
print(f' {f} ({size_mb:.1f} MB)')
"
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.
- 12d ago First seen · 133 lines · 34 tokens per session scan A 2ec0ddbe4fad
search-stac is a skill published in the GitHub repository opengeos/geoai-skills (30 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 937 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
geoai-orchestrator
Route genuinely ambiguous or multi-stage geospatial work across specialist skills while enforcing shared CRS, validity, leakage, units, verification, and reproducibility rules. Use for requests spanning multiple stages such as acquisition, imagery, modeling, analysis, and map delivery, or for an explicit end-to-end…
google-earth-engine
Invoke when Earth Engine, GEE, ee., or geemap is named; when work needs its server-side catalog; or when choosing Earth Engine versus local xarray or desktop processing for a large area or long archive. Covers image collections, masking, compositing, reducers, zonal statistics, time series, classification, quota-aware…
point-cloud-lidar
LiDAR and point cloud processing: PDAL pipelines, LAS/LAZ/COPC handling, ground classification, DTM/DSM/CHM generation, canopy and building metrics, and photogrammetric (SfM) point clouds. Use when the primary input is LAS, LAZ, COPC, LiDAR, or an unstructured 3D point cloud. This skill owns vertical datum agreement…
change-detection
Change analysis, once the observations are comparable. Not for cases whose blocker is comparability itself: mixed sensors, product levels or processing baselines to remote-sensing-analysis, undocumented vertical datums to point-cloud-lidar, multi-decade archive trends over large areas to google-earth-engine. Matching…
geo-deep-learning
Invoke before recommending, training, or auditing a neural method for geospatial imagery, including vision transformers, U-Net/DeepLab/SegFormer, object detection, pixel classification, building/road extraction, and EO foundation-model fine-tuning. Also invoke for neural chip-split validity, IoU/accuracy claims…
remote-sensing-analysis
Always invoke for classical analysis, classification, validation, or comparability of satellite, aerial, or drone imagery. This skill owns sensor, product, processing-level and processing-baseline harmonization, including multi-date inputs; add change-detection only after comparable observations exist. Two scenes of…