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 iowarp/clio-kit --skill dataset-stagegit clone --depth 1 https://github.com/iowarp/clio-kitWrote 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/iowarp/clio-kit/dataset-stage)<a href="https://agentmods.dev/skills/iowarp/clio-kit/dataset-stage"><img src="https://agentmods.dev/badge/skills/iowarp/clio-kit/dataset-stage/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/iowarp/clio-kit/dataset-stage"><img src="https://agentmods.dev/badge/skills/iowarp/clio-kit/dataset-stage.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 | $0.00047 | $0.00950 |
| Opus 5.5 | $0.00019 | $0.00380 |
| Sonnet 5.5 | $0.00009 | $0.00190 |
| Haiku 4.5 | $0.00005 | $0.00095 |
Grade A, and why
dataset-stage 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 9d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dataset Staging
Two catalogs answer "where is data about X", and they hold different things. The step everyone forgets is the last one: a dataset that has only been found is metadata. Nothing can read it until it is staged.
Which catalog
clio-ndp — the National Data Platform. Public, broad, organised by
publishing organisation.
clio-scientific-catalog — datasets an operator has registered on this
deployment. Narrower, curated, and the one that knows about local data the public
platform has never heard of.
Search both when the answer matters. They do not overlap in any predictable way.
National Data Platform
clio-ndp:list_organizations— who publishes here. On a broad topic this narrows the search far more effectively than more keywords.clio-ndp:search_datasets— term-based or field-specific.clio-ndp:get_dataset_details— the full metadata for one. Read this before staging. It says what the data actually is, and staging is the step that costs time and disk.clio-ndp:stage_resource— download an HTTP(S) or OSDF/Pelican resource, returninglocal_path, size, and content type.
local_path is the whole point. It is what you pass to the readers — see
dataset-explore. The returned content type tells you which
reader: a .gz needs decompressing first, a .parquet goes to the Parquet
server, an .h5 to HDF5.
The operator catalog, and its handoff to a pipeline
clio-scientific-catalog:scientific_dataset_search returns bounded intrinsic
summaries. scientific_dataset_describe returns one exact record plus a
top-level dataset_descriptor.
Pass
dataset_descriptorunchanged asconfig.dataset_descriptortoclio-jarvis:jarvis_add_step. Do not rebuild it, do not extract a path from it, do not simplify it. It is the identifier the pipeline resolves; anything derived from it loses what makes the reference exact.
This is the same shape as the Spack handoff in
cluster-run: an opaque token that must survive the trip
intact. Reconstructing it is the failure both times.
What ships with it
1 file 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.
- 9d ago First seen · 90 lines · 47 tokens per session scan A 8a93fd184f4a
dataset-stage is a skill published in the GitHub repository iowarp/clio-kit (30 stars, last pushed 8d ago), licensed BSD-3-Clause. It adds 47 tokens to every session and 950 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 2026-10-08.
Other skills, from other repositories
bio-ortholog-inference
Pull pre-computed ortholog calls from public databases (OrthoDB, Ensembl Compara, OMA browser, eggNOG, PANTHER, KEGG Orthology, HomoloGene) via their REST APIs. Use when orthologs are already curated upstream, when the question is "what is the X ortholog of Y" rather than "how to infer orthology de novo", when…
admet_genetic
ADMET-guided genetic molecule optimization workflow from seed SMILES; use when the agent needs to build or run an RDKit/SA-Score/ADMET-AI GA pipeline for molecule optimization, enforce molecule lineage logs, render optimization-history HTML dashboards, and write candidate triage reports.
paper-figures
Use this skill to produce standalone, publication-ready PNG graphics and reproducible matplotlib scripts from tabular data (CSVs or DataFrames). It renders numerical data into formal scientific visualizations—including scatter, line, bar, pie, ring, bubble, tornado, KDE, violin, box, heatmap, histogram, and area…
paper-planning
Guides pre-writing planning for academic papers with 4 structured steps: story design (task-challenge-insight-contribution-advantage), experiment planning (comparisons + ablations), figure design (pipeline + teaser), and 4-week timeline management. Includes counterintuitive planning tactics (write a mock rejection…
paper-review
Guides self-review of YOUR OWN academic paper before submission with adversarial stress-testing. Core method: three passes (adversarial deep read; 5-aspect checklist — contribution sufficiency, writing clarity, results quality, testing completeness, method design; mechanical consistency scans and experimental protocol…
experiment-craft
Use this skill when the user wants to debug, diagnose, or systematically iterate on an experiment that already exists, or when they need a structured experiment log for tracking runs, hypotheses, failures, results, and next steps during active research. Apply it to underperforming methods, training that will not…