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-exploregit 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-explore)<a href="https://agentmods.dev/skills/iowarp/clio-kit/dataset-explore"><img src="https://agentmods.dev/badge/skills/iowarp/clio-kit/dataset-explore/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-explore"><img src="https://agentmods.dev/badge/skills/iowarp/clio-kit/dataset-explore.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 | $0.00061 | $0.01637 |
| Opus 5.5 | $0.00024 | $0.00655 |
| Sonnet 5.5 | $0.00012 | $0.00327 |
| Haiku 4.5 | $0.00006 | $0.00164 |
Grade A, and why
dataset-explore 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dataset Exploration
Every format here separates structure from data. Read the structure first. It is small, and it tells you whether the data is something you can afford to read at all.
Decompress first if you have to
A .gz file is not readable by any of the format tools. Run
clio-compression:decompress_file_tool and work with what it produces. Check available disk space and any trusted uncompressed-size metadata first.
A gzip footer is not a reliable size bound for large or concatenated archives;
this decompressor has no output-size limit. Do not expand an untrusted or
unbounded archive merely to inspect its contents.
Pick the reader by format, not by preference
| File | Server | Opening move |
|---|---|---|
.h5, .hdf5 |
clio-hdf5 |
open_file, then list_keys |
.bp, .bp5 |
clio-adios |
list_bp5, then inspect_variables |
.parquet |
clio-parquet |
summarize_tool |
HDF5 holds a file open — this is the trap
The HDF5 server is stateful. clio-hdf5:open_file opens the current file, and
every tool after it operates on that file without taking a path.
- Opening another file changes the current file. Close the previous one and confirm the new identity before attributing subsequent results.
clio-hdf5:get_filenamesays which file is actually open. When results look wrong, check this before anything else.- Close when finished.
hdf5_batch_read and hdf5_aggregate_stats also require the current file;
their paths refer to datasets inside it. hdf5_parallel_scan instead accepts
a directory and filename pattern for a multi-file structure scan.
The argument names are not guessable
Nothing on this server takes file_path. Getting one wrong is worse than a
plain failure: open_file fails, then every later call answers "No file
currently open", which reads as an empty file rather than a failed open.
| Call | Argument |
|---|---|
open_file |
path (the FILE) |
list_keys, get_shape, get_dtype, list_attributes |
path (a path INSIDE the file) |
read_attribute |
path and name |
read_partial_dataset |
path, plus start and count as comma-separated strings, not lists |
hdf5_batch_read, hdf5_aggregate_stats |
paths, a comma-separated string |
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 · 136 lines · 61 tokens per session scan A 0d11d4e01e78
dataset-explore is a skill published in the GitHub repository iowarp/clio-kit (30 stars, last pushed 8d ago), licensed BSD-3-Clause. It adds 61 tokens to every session and 1,637 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…