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 responsible-genai-hackweek/nicer-nisar --skill nisar-snow-predictgit clone --depth 1 https://github.com/responsible-genai-hackweek/nicer-nisarWrote 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/responsible-genai-hackweek/nicer-nisar/nisar-snow-predict)<a href="https://agentmods.dev/skills/responsible-genai-hackweek/nicer-nisar/nisar-snow-predict"><img src="https://agentmods.dev/badge/skills/responsible-genai-hackweek/nicer-nisar/nisar-snow-predict/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/responsible-genai-hackweek/nicer-nisar/nisar-snow-predict"><img src="https://agentmods.dev/badge/skills/responsible-genai-hackweek/nicer-nisar/nisar-snow-predict.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 | $0.00108 | $0.01635 |
| Opus 5 | $0.00054 | $0.00817 |
| Sonnet 5 | $0.00022 | $0.00327 |
| Haiku 4.5 | $0.00011 | $0.00163 |
Grade C, and why
nisar-snow-predict scanned grade C with 1 finding 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 11d 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
Earthdata Login via `~/.netrc`; CMR search did not. How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Predicting snow depth change
The user-facing half of the system (workflow B in CLAUDE.md). Deterministic, pinned, and it never trains. Your job here is at the two edges — turning a request into a query, and turning a raster into an honest sentence. Everything between those is called, not reasoned about.
request → list_acquisitions(aoi, season) → user picks → predict_snow_depth() → report
^ you ^ them ^ you
1. Parse the request
from nisar_snow import config as C
from nisar_snow.catalog import list_acquisitions
pairs = list_acquisitions(C.AOI_BOUNDS_LONLAT, season=("2025-12-01", "2026-01-31"))
Defaults that are almost always right: aoi_lonlat=C.AOI_BOUNDS_LONLAT (the NIVAL
flight box) and season=("2025-11-01", "2026-04-30"). Only widen the AOI if the
user names somewhere else — and if they do, say plainly that the model was fit at
Mores Creek and the ancillary layers are the NIVAL LiDAR, so it does not transfer.
list_acquisitions hits public CMR and needs no auth. It applies the peak-SWE
cutoff itself (invariant 3, water year). Do not filter by date again afterwards;
you will double-apply it.
2. Present pairs. Do not pick one.
Invariant 2. list_acquisitions offers, the user chooses. Show ref_date,
sec_date, track, baseline_days, and let them decide. This is the whole point
of the availability-first design — the user picks from what flew rather than naming
a date the satellite did not image.
If they say "just use the best one," that is explicit delegation and you may pick — say which you picked and why. Silently picking is the failure mode.
Expect ~10 usable ascending pairs, tracks 077 and 149, over Nov 2025 – Apr 2026. Zero descending are usable here.
3. Predict
from nisar_snow.predict import predict_snow_depth, MeltCorrupted
prod = predict_snow_depth(C.AOI_BOUNDS_UTM, granule_id, model_id)
Or python scripts/run_predict.py <model_id> <granule_id>. Granule bytes need
Earthdata Login via ~/.netrc; CMR search did not.
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.
- 11d ago First seen · 134 lines · 108 tokens per session scan C 3d889f672f21
nisar-snow-predict is a skill published in the GitHub repository responsible-genai-hackweek/nicer-nisar (2 stars, last pushed 13d ago), licensed BSD-3-Clause. It adds 108 tokens to every session and 1,635 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
analyze-project
Rigor Analyze / Rigor Audit read-only skill for deep learning research repositories. Use when the user wants to read and understand a repository, inspect model structure and training or inference entrypoints, review configs and insertion points, or flag suspicious implementation patterns without modifying code or…
torchdrug
Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…
pyhealth
Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer…
deepspot-m
Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.