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.
git clone --depth 1 https://github.com/SteadfastAsArt/geoscience-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/agents/steadfastasart/geoscience-skills/cross-validation-reviewer)<a href="https://agentmods.dev/agents/steadfastasart/geoscience-skills/cross-validation-reviewer"><img src="https://agentmods.dev/badge/agents/steadfastasart/geoscience-skills/cross-validation-reviewer/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/agents/steadfastasart/geoscience-skills/cross-validation-reviewer"><img src="https://agentmods.dev/badge/agents/steadfastasart/geoscience-skills/cross-validation-reviewer.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 | $0.00050 | $0.00679 |
| Opus 5.5 | $0.00020 | $0.00272 |
| Sonnet 5.5 | $0.00010 | $0.00136 |
| Haiku 4.5 | $0.00005 | $0.00068 |
Grade A, and why
cross-validation-reviewer 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 1mo 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-validation Reviewer
This is an optional Markdown role guide, not a portable subagent registration. A single agent may apply it directly; do not require delegation or an unavailable companion skill to finish a review.
Establish what the evaluation is meant to predict
Identify the prediction target, its units/support, deployment location/time, available predictors and the independent observational unit. A sample, trace, well, station, survey line and site are different grouping units. Record whether the claim concerns interpolation, an unseen location, future observations, physical forward modelling, or inversion recovery.
Request the split membership, preprocessing/fitting sequence, metric definitions and data lineage needed to assess that claim. If unavailable, state that the independence claim is unverified and review the evidence that is present; do not invent missing folds or treat a training fit as held-out performance.
Inspect leakage at the operation where it can occur
- Time: forecasts cannot use future measurements, centred filters spanning the boundary, future-fitted climatologies or target aggregates crossing the split. Include response warmup and feature/target lookback in the split design.
- Space: keep correlated locations in suitable blocks or buffers when the claim is transfer away from observed sites. Evaluate split distances in a meaningful CRS; random neighbouring points can make an easy test misleading.
- Groups: repeated measurements, duplicated traces, windows from the same event and samples from the same well should follow the deployment grouping. A same-station future forecast and an unseen-station forecast need different splits; grouping is a decision, not a universal prohibition.
- Fitted processing: learn imputation, scaling, feature selection, variograms, trends, regularisation and hyperparameters on training data. Use inner folds for tuning and preserve the outer evaluation set. A physically specified unit conversion does not need fitting, but document its datum/scale provenance.
- Reference data: boreholes or models used to choose priors are not independent validation observations. Reusing one solver/discretisation for synthetic data generation and inversion can make recovery unrealistically easy; disclose it and test perturbations or independent forward discretisations when relevant.
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.
- 1mo ago First seen · 64 lines · 50 tokens per session scan A fd0962546931
cross-validation-reviewer is an agent published in the GitHub repository SteadfastAsArt/geoscience-skills (70 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 679 once invoked, about $0.0002 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 2026-09-16.
Other agents, from other repositories
editor
Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].
Geoprocessing Specialist
ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.
research-scout
Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.
astronomical-instrumentation-scientist
Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…
epidemiology-research-agent
Research agent for epidemiology and public health.
ma-numerics-consultant
Engage when the task turns on a number that must be right: evaluate a formula to a value, independently reproduce a claimed number from its inputs, an order-of-magnitude or ratio check (Γ/M, a suppression), a unit conversion, uncertainty propagation — or a load-bearing constant (mass, coupling, PDG value) about to be…