CRS Sanity Check

CRS Sanity Check is a skill for Claude Code, Codex from GeoRetina/Arion. It costs 19 tokens per session (183 once invoked), scanned A, original, GPL-3.0.

A check of coordinate systems, measurement units, and assumptions about changing data between map projections. A coordinate system defines how locations are represented on a map.

In plain words
What is it for?
Use it before geospatial analysis to validate the data's coordinate system, units, and planned reprojections.
Why use it?
It helps prevent analyses based on mismatched locations, units, or reprojection choices. Reprojection means converting map data from one coordinate system to another.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

Good fit Use it before geospatial analysis to validate the data's coordinate system, units, and planned reprojections.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/georetina/arion/crs-sanity-check
Install

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.

Any agent
npx skills add GeoRetina/Arion --skill crs-sanity-check
Clone the repo
git clone --depth 1 https://github.com/GeoRetina/Arion

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for CRS Sanity Check

README.md
[![agentmods](https://agentmods.dev/badge/skills/georetina/arion/crs-sanity-check/github.svg)](https://agentmods.dev/skills/georetina/arion/crs-sanity-check)
Your own site
<a href="https://agentmods.dev/skills/georetina/arion/crs-sanity-check"><img src="https://agentmods.dev/badge/skills/georetina/arion/crs-sanity-check/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.

agentmods 80×15 button for CRS Sanity Check

Your own site · 80×15
<a href="https://agentmods.dev/skills/georetina/arion/crs-sanity-check"><img src="https://agentmods.dev/badge/skills/georetina/arion/crs-sanity-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 183 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.00183
Opus 5.5 $0.00008 $0.00073
Sonnet 5.5 $0.00004 $0.00037
Haiku 4.5 $0.00002 $0.00018

Measured 1mo ago against content hash 97ea6e33fb89, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

CRS Sanity Check 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.

resources/skills/bundled/crs-sanity-check/SKILL.md · 28 lines

The source is not reproduced here

Licensed GPL-3.0

The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Changes

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.

  1. 1mo ago First seen · 28 lines · 19 tokens per session scan A 97ea6e33fb89

Subscribe to this mod's changes

CRS Sanity Check is a skill published in the GitHub repository GeoRetina/Arion (86 stars, last pushed 6mo ago), licensed GPL-3.0. It adds 19 tokens to every session and 183 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

gis-skills

Use when processing geospatial data, publishing map services, querying spatial databases, performing geometry operations, running desktop or cloud-native GIS apps, or building web map applications. Index of 40 skills: GDAL, GeoServer, QGIS, PostGIS, DuckDB Spatial, SpatiaLite, JTS, GeoPandas, Shapely, CesiumJS…

znlgis/opengis-skills · 117 tokens

czml-model

CZML 3D models (glTF) for vehicles, aircraft, spacecraft, or any 3D asset placed on the globe, including per-node transformations and Model Articulations for jointed or moving parts. Use when the intent describes a 3D model, glTF asset, vehicle/aircraft/rocket model, or a model with moving, articulated, or transformed…

CesiumGS/cesiumjs-ai-starter-app · 83 tokens

czml-reference-properties

CZML reference properties that link one entity's property to another entity's value, including a single reference, an array of references (e.g. building a polygon's corners from other entities' positions), and referencing non-position properties like colors or materials. Use when the intent describes an entity that…

CesiumGS/cesiumjs-ai-starter-app · 84 tokens

czml-time-dynamic-motion

CZML time-dynamic motion: interpolated/sampled positions over an epoch and trails for orbiting, flying, or otherwise moving entities. Use when the intent describes an entity moving, orbiting, flying, or changing position over time (not a single static point).

CesiumGS/cesiumjs-ai-starter-app · 61 tokens

czml-box

CZML box shapes — closed rectangular cuboids for buildings, containers, or simple 3D blocks. Use when the intent describes a box, cube, rectangular volume, block, or cuboid shape, including solid, translucent, outlined, or wireframe-only variants.

CesiumGS/cesiumjs-ai-starter-app · 58 tokens

czml-clock

CZML document-level clock controlling the viewer's timeline: start/stop interval, current time, playback multiplier, and looping behavior. Use when the intent mentions a clock, timeline, playback speed, looping, or specific start/stop times for the whole scene.

CesiumGS/cesiumjs-ai-starter-app · 56 tokens