Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/responsible-genai-hackweek/nicer-nisarnpx agentmods add skills/responsible-genai-hackweek/nicer-nisar/nisar-snow-verifyWrote 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-verify)<a href="https://agentmods.dev/skills/responsible-genai-hackweek/nicer-nisar/nisar-snow-verify"><img src="https://agentmods.dev/badge/skills/responsible-genai-hackweek/nicer-nisar/nisar-snow-verify/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-verify"><img src="https://agentmods.dev/badge/skills/responsible-genai-hackweek/nicer-nisar/nisar-snow-verify.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 | $0.00107 | $0.01669 |
| Opus 5 | $0.00053 | $0.00834 |
| Sonnet 5 | $0.00021 | $0.00334 |
| Haiku 4.5 | $0.00011 | $0.00167 |
Grade A, and why
nisar-snow-verify 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Re-verifying the facts underneath
Every number in config.py and every VERIFIED claim in CLAUDE.md was checked
against the live archive in August 2026. The archive is not static: a full validated
reprocessing of the L0–L3 backlog is targeted for Q4 2026, and CRIDs have already
churned P00407 → X0500x → P05006 → P05012 → P05023.
This skill is the loop that keeps those claims honest.
Run the reconnaissance
python scripts/recon.py # cached
python scripts/recon.py --nocache # against the live archive -- do this one
It re-derives, against a real granule, the facts in EXPECT:
EXPECT = dict(epsg=32611, res=80.0, window=(2888, 2994, 3469, 3568), cells=10494,
frame=24, track=77, direction="Ascending", cc_labels={0, 1},
col_edge0=-74, row_edge0=-14)
A disagreement means one of two things and you must decide which: the archive
changed (reprocessing), or the code drifted. Check git log on
nisar_snow/gunw.py and nisar_snow/config.py before concluding it was the archive.
col_edge0=-74, row_edge0=-14 is the grid-alignment fact and the most valuable line
in that table. The AOI's first coarse cell starts 74 LiDAR pixels left and 14 up of
the block boundary — 37.0 m and 7.0 m, 46% and 9% of a cell. A naive
.reshape(-1,160,160).mean() is displaced by exactly that and looks entirely
normal. grid.block_edges computes cumulative edges from both geotransforms;
test_naive_reshape_is_wrong pins it. If that test ever gets "simplified," this is
what breaks.
The tagging discipline
Three tags, used in CLAUDE.md and in nisar-data-access:
- VERIFIED — checked against the live archive or a real file, method stated.
- INFERRED — a consistent pattern across real granules, not read from a spec.
- OPEN / UNVERIFIED — documentation only, or not looked at.
Do not promote a tag without doing the check. Promotion is the failure mode: an INFERRED claim quoted twice starts reading as established. Demotion is equally required — if a reprocessing invalidates a VERIFIED fact, move it back and say when.
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 · 114 lines · 107 tokens per session scan A 83c22d55856d
nisar-snow-verify is a skill published in the GitHub repository responsible-genai-hackweek/nicer-nisar (2 stars, last pushed 14d ago), licensed BSD-3-Clause. It adds 107 tokens to every session and 1,669 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
mechanical-engineering-research
Apply source-aware mechanical-engineering judgment to research, analysis, coding, writing, teaching, research identity, and release work. Use for thermal-fluid systems, heat transfer, fluid mechanics, thermodynamics, HVAC, energy systems, turbomachinery, piping, multiphase flow, experiments, correlations, CFD…
research-schematic-design
Create publication-quality, editable scientific and engineering schematics with explicit physical meaning, exact labels, visual hierarchy, and provenance. Use for experimental facilities, thermal-fluid mechanisms, workflows, graphical abstracts, system architectures, or research diagrams.
thermal-fluid-analysis
Analyze thermal-fluid engineering systems, experiments, CFD, and correlations with explicit assumptions, validity limits, uncertainty, and mechanism-based interpretation. Use for heat transfer, fluid mechanics, phase change, HVAC, energy systems, turbomachinery, piping, or thermal management.
research-data-analysis
Design and analyze engineering experiments or simulations using baseline cases, hypothesis-driven DOE, traceable data processing, defensible plots, uncertainty, and validation. Use for CFD, laboratory data, ML workflows, parameter studies, or research code.
research-lab
A research workflow for questions that can be tested with evidence, such as comparing models or software. It defines the question, baseline, candidates, data, measurements, and decision rules before running or resuming an experiment.
alternative-coffee-intelligence
Alternative Slowbar coffee intelligence — scientific analysis from seed to cup using First Principle + System Thinking. Covers: varieties, terroir, cultivation, disease diagnosis, processing, roasting physics/chemistry, extraction science, brewing, business strategy, storytelling. ALWAYS trigger for coffee-related…