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 chart-selectgit 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/chart-select)<a href="https://agentmods.dev/skills/iowarp/clio-kit/chart-select"><img src="https://agentmods.dev/badge/skills/iowarp/clio-kit/chart-select/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/chart-select"><img src="https://agentmods.dev/badge/skills/iowarp/clio-kit/chart-select.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 | $0.00048 | $0.01067 |
| Opus 5.5 | $0.00019 | $0.00427 |
| Sonnet 5.5 | $0.00010 | $0.00213 |
| Haiku 4.5 | $0.00005 | $0.00107 |
Grade A, and why
chart-select 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chart Selection
The chart type follows from the question. Working the other way — picking a familiar chart and fitting the data to it — is how a figure ends up answering something nobody asked.
Question to chart
| The question | Chart |
|---|---|
| How does y change with x, where x is ordered | line |
| How does this change over time | time series line |
| How do a few categories compare | bar |
| Are these two variables related | scatter |
| How is one variable distributed | histogram |
| Which of many variables move together | heatmap of correlations |
Two rules behind the table:
Lines imply continuity. A line between two points says the values in between are meaningful. Over categories they are not, and the line is a claim about nothing. Use bars.
Bars imply a magnitude from zero. A bar chart with a truncated y axis exaggerates differences — the length of the bar is the message, and it is wrong. Truncating a line axis is fine, because a line's message is the shape.
Distributions
A histogram's bin width is a choice that changes the conclusion. Too few bins hides a second peak; too many turn a distribution into noise. Try more than one before believing a shape — a bimodal distribution reported as unimodal is a finding lost to a default.
A histogram shows one variable. Comparing distributions across groups is a different figure, not several histograms the reader has to hold at once.
Log scales
Use a log axis when the data spans orders of magnitude, or when the interesting relationship is multiplicative. Runtime against problem size, particle counts, error against resolution — all naturally log.
An ordinary log axis cannot show zero or negative values. State how those observations are handled; never silently discard them.
Distinguish the axes: on a semilog-y plot, y = A exp(kx) is a straight
line; on a log-log plot, y = A x^p is a straight line. These are different
relationships. Label both axes and do not infer a fitted model from appearance
alone. Use the user's stated data for a conceptual question; an unrelated file
in the working directory does not contradict their description.
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 · 115 lines · 48 tokens per session scan A c20173ed15dd
chart-select is a skill published in the GitHub repository iowarp/clio-kit (30 stars, last pushed 8d ago), licensed BSD-3-Clause. It adds 48 tokens to every session and 1,067 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…