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 tondevrel/scientific-agent-skills --skill pyprojgit clone --depth 1 https://github.com/tondevrel/scientific-agent-skillsWrote 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/tondevrel/scientific-agent-skills/pyproj)<a href="https://agentmods.dev/skills/tondevrel/scientific-agent-skills/pyproj"><img src="https://agentmods.dev/badge/skills/tondevrel/scientific-agent-skills/pyproj/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/tondevrel/scientific-agent-skills/pyproj"><img src="https://agentmods.dev/badge/skills/tondevrel/scientific-agent-skills/pyproj.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 | $0.00076 | $0.02770 |
| Opus 5 | $0.00038 | $0.01385 |
| Sonnet 5 | $0.00015 | $0.00554 |
| Haiku 4.5 | $0.00008 | $0.00277 |
Grade A, and why
pyproj 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 10d 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PyProj - Coordinate Projections and Geodetic Math
PyProj is essential for any spatial analysis that requires high precision. It allows you to transform coordinates between thousands of different reference systems and compute distances on the Earth's ellipsoidal surface using the most accurate formulas (Vincenty, Karney).
When to Use
- Converting GPS coordinates (WGS84) to local projected systems (e.g., UTM, Albers, State Plane).
- Calculating precise distances, bearings, and areas on the Earth's surface (Geodetic math).
- Defining custom Coordinate Reference Systems (CRS).
- Handling transformations between different vertical datums.
- Working with "Great Circle" paths and geodesics.
- Identifying the best UTM zone for a specific location.
Reference Documentation
Official docs: https://pyproj4.github.io/pyproj/
PROJ (Engine): https://proj.org/
EPSG Registry: https://epsg.io/ (Essential for finding CRS codes)
Search patterns: pyproj.Transformer, pyproj.CRS, pyproj.Geod
Core Principles
CRS (Coordinate Reference System)
A definition of how numbers (coordinates) map to the real world. Can be defined via EPSG codes (EPSG:4326), PROJ strings, or WKT (Well-Known Text).
Transformer
An object optimized for converting many points from one CRS to another. Always use Transformer for bulk operations rather than one-off calls.
Geod
A class for performing "ellipsoid math". Use this for calculating distances on Earth without projecting to a flat map.
Quick Reference
Installation
pip install pyproj
Standard Imports
import pyproj
from pyproj import CRS, Transformer, Geod
Basic Pattern - Transformation
from pyproj import Transformer
# 1. Define the transformation (WGS84 to Web Mercator)
# always_xy=True ensures (lon, lat) order instead of PROJ default (lat, lon)
transformer = Transformer.from_crs("EPSG:4326", "EPSG:3857", always_xy=True)
# 2. Transform coordinates
lon, lat = -74.006, 40.7128 # NYC
x, y = transformer.transform(lon, lat)
print(f"Projected Meters: X={x:.2f}, Y={y:.2f}")
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.
- 10d ago First seen · 298 lines · 76 tokens per session scan A 38bc1b0280e2
pyproj is a skill published in the GitHub repository tondevrel/scientific-agent-skills (21 stars, last pushed 7mo ago), licensed MIT. It adds 76 tokens to every session and 2,770 once invoked, about $0.0004 per session on Opus 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.
Other skills, from other repositories
jupyter-notebook
Iterative Python via live Jupyter kernel (hamelnb).
bioservices
Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database analysis, ID mapping across services. For quick single-database lookups use gget; for sequence/file manipulation use…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
pennylane
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…
cuopt-numerical-optimization-api
LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.
rocm-kernels
Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…