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 geospatial-mapgit 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/geospatial-map)<a href="https://agentmods.dev/skills/iowarp/clio-kit/geospatial-map"><img src="https://agentmods.dev/badge/skills/iowarp/clio-kit/geospatial-map/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/geospatial-map"><img src="https://agentmods.dev/badge/skills/iowarp/clio-kit/geospatial-map.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 | $0.00051 | $0.01190 |
| Opus 5.5 | $0.00020 | $0.00476 |
| Sonnet 5.5 | $0.00010 | $0.00238 |
| Haiku 4.5 | $0.00005 | $0.00119 |
Grade A, and why
geospatial-map 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Geospatial Mapping
Spatial mistakes do not raise errors. A bounding box computed over malformed features, or a place name the model invented coordinates for, produces a map that renders perfectly and is wrong.
Validate before anything spatial
clio-geo:validate_geojson checks the supported GeoJSON structure. Run it before spatial
operations, then inspect coordinate ranges, CRS and geometric validity. A
successful structural check does not establish valid topology or correct CRS.
Then clio-geo:inspect_geojson for geometry types and counts, feature count,
property keys and bounding box in one call — the fastest way to find out what a
file actually holds. clio-geo:summarize_geojson gives the readable version
with sample properties.
Two bounding-box tools, and they can disagree
clio-geo:feature_bbox and clio-geo:bounding_box both return
[min_lon, min_lat, max_lon, max_lat].
On a clean file they agree. On a file with malformed geometries they need not, because they differ in what they include. Validate first and the question does not arise; skip validation and you have a box you cannot account for.
They do not even take the same argument. feature_bbox wants source;
bounding_box wants geojson. That split runs through the whole server: the
four tools ported in from the old geojson server (inspect_geojson,
validate_geojson, summarize_geojson, feature_bbox) take source, while
geo's own tools take geojson, data_path, layers or query. Passing the
wrong one returns a missing-required-argument error that reads as though the
file were absent.
clio-geo:bounding_box also takes buffer_km for padding, which is what you want
when the box is being used to query a region rather than describe one.
Never guess coordinates
clio-geo:geocode looks a place name up against OpenStreetMap Nominatim and
returns real coordinates. Writing coordinates from memory is a fabricated result
that looks exactly like a real one.
Geocoding is ambiguous by nature — several matches come back for a name. Pick using the returned metadata, and say which one was used.
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 · 110 lines · 51 tokens per session scan A f7ff328a7a66
geospatial-map is a skill published in the GitHub repository iowarp/clio-kit (30 stars, last pushed 8d ago), licensed BSD-3-Clause. It adds 51 tokens to every session and 1,190 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…