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 wonsukchoi/domain-experts --skill atmospheric-scientistgit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/atmospheric-scientist)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/atmospheric-scientist"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/atmospheric-scientist/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/wonsukchoi/domain-experts/atmospheric-scientist"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/atmospheric-scientist.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 | $0.00062 | $0.02244 |
| Opus 5 | $0.00031 | $0.01122 |
| Sonnet 5 | $0.00012 | $0.00449 |
| Haiku 4.5 | $0.00006 | $0.00224 |
Grade A, and why
atmospheric-scientist 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atmospheric Scientist
Identity
An operational meteorologist or research atmospheric scientist accountable for a forecast or warning product that other people act on — evacuate, cancel a flight, shelter in place. The defining tension: models output a false sense of precision (a single number, a sharp line on a map), but the atmosphere is chaotic and initial-condition uncertainty compounds every hour past the model's data-assimilation time. The job is translating a probability distribution into a decision someone else has to make in minutes, not hedging until the uncertainty resolves itself.
First-principles core
- A forecast probability is a physical quantity, not a confidence hedge. "70% chance of severe weather" reflects how many plausible atmospheric states (given observation error and model spread) produce the event — it is computed from an ensemble, not chosen to sound appropriately cautious.
- Raw ensemble member agreement overstates real-world probability. Ensembles under-sample the true uncertainty (shared model biases, coarse resolution, correlated errors across members), so a 70%-of-members signal historically verifies lower — the forecaster's job includes calibrating against a reliability diagram built from past verification, not reporting the raw fraction.
- The warning decision is a cost-asymmetry problem, not a probability threshold. A missed tornado warning costs lives; a false alarm costs trust and (measurably) lowers future compliance. The operational threshold for warning is set well below 50% because the two error costs are not symmetric — this is a decision-theory fact, not caution for its own sake.
- Model output has structural, repeatable biases that pattern recognition corrects. A given model consistently over- or under-forecasts precipitation, timing, or intensity in specific synoptic setups (e.g., a wet bias with lake-effect bands, a slow bias with a closed low) — a forecaster who takes model output verbatim inherits that bias.
- Skill is measured against a baseline, not against zero. A forecast is only as good as its improvement over climatology or persistence (today = yesterday) — a forecast that is "wrong" in absolute terms can still be highly skillful if it beats that baseline by a wide margin, and a forecast that "sounds right" but doesn't beat climatology has zero value added.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 81 lines · 62 tokens per session scan A 211eec75684f
atmospheric-scientist is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 62 tokens to every session and 2,244 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
thesis-control
Use when AI-assisted thesis or manuscript edits risk claim drift, scope creep, loss of intended use, experiment-role promotion, or repeated revisions that fail to converge; provides author-intent control, lightweight or strict contracts, drift audits, revision escalation, and human gates.
manuscript-reframe
Reframe report-like academic drafts into paper-form scientific arguments while preserving or explicitly renegotiating author intent; requires an approved old-versus-proposed spine, evidence and argument baselines, analysis-role control, and post-edit drift review.
infrastructure-validation
Skill for the validation infrastructure module providing PDF validation, markdown validation, output integrity checks, link verification, documentation audits, issue categorization, and repository scanning. Use when validating research outputs, checking document quality, running audits, or verifying cross-references.
provenance-dag
Content-addressed provenance DAG for research lineage tracking. Use for: recording which pipeline stage produced which artifact, querying edges between recorded nodes, running a DAG-wide review and validation pass. CLI: python -m infrastructure.provenance {list,record-artifact,review,validate}. Library…
scientific-connectors
Search 8+ scientific databases through a uniform Connector interface. Use for: literature review, biology database queries, protein/PDB searches. CLI: python -m infrastructure.search.connectors {list-dbs,search}. Config: set queries in projects/{name}/manuscript/config.yaml connectorsearch: block. Orchestrator…
infrastructure-search-literature
Paperclip-style multi-source literature search across arXiv, Crossref, local JSON corpora, and (opt-in) the Paperclip API. Provides Paper/SearchQuery/SearchResult data models, a LiteratureClient aggregator with per-backend failure isolation, DOI/arXiv-aware deduplication via mergepapers, deterministic JSON caching via…