geotessera copilot-instructions.md

geotessera copilot-instructions.md is an instructions file for GitHub Copilot from ucam-eo/geotessera. It costs 2,084 tokens per session, scanned A, original, MIT.

Project guidance for GeoTessera, a Python library that downloads, processes, exports, and visualizes numerical representations of Sentinel-1 and Sentinel-2 satellite images.

In plain words
What is it for?
Use it when developing or testing GeoTessera features involving satellite embeddings, tile lookup, GeoTIFF or NPY export, GIS processing, or visualisation.
Why use it?
It explains how the library finds image tiles, handles downloads, checks file integrity, and works with geospatial data. This helps an agent follow the existing architecture and required Python version.

Instructions file for GitHub Copilot

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.

agentmods
npx agentmods add instructions/ucam-eo/geotessera/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/ucam-eo/geotessera

Made for: GitHub Copilot.

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 geotessera copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ucam-eo/geotessera/copilot-instructions.svg)](https://agentmods.dev/instructions/ucam-eo/geotessera/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/ucam-eo/geotessera/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/ucam-eo/geotessera/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,084 This file is loaded in full into every session.
When invoked 2,084 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original 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 $0.02084 $0.02084
Opus 5 $0.01042 $0.01042
Sonnet 5 $0.00417 $0.00417
Haiku 4.5 $0.00208 $0.00208

Measured 5d ago against content hash f6a35a3eb28d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

geotessera copilot-instructions.md 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 5d 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.

.github/copilot-instructions.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot Instructions for GeoTessera

Project Overview

GeoTessera is a Python library for accessing and working with Tessera geospatial foundation model embeddings. The library provides tools to download, process, and visualize satellite imagery embeddings from Sentinel-1 and Sentinel-2 data at 10m resolution.

Core Architecture

  • Two-step workflow: Retrieve embeddings (numpy arrays) → Export to desired format (GeoTIFF/NPY)
  • Registry system: Parquet-based metadata registry for efficient tile lookup
  • 0.1-degree grid: Tiles cover ~11km × 11km, named by center coordinates
  • Direct HTTP downloads: On-demand tile fetching with automatic cleanup
  • Hash verification: SHA256 checksums ensure data integrity by default

Technology Stack

Core Dependencies

  • Python: 3.12 or 3.13 required (requires-python = ">=3.12")
  • CLI Framework: typer with rich for interactive output
  • Geospatial: rasterio, geopandas, rioxarray for GIS operations
  • Data Processing: numpy, pandas, pyarrow (for Parquet registry)
  • Visualization: matplotlib, scikit-learn (PCA), scikit-image
  • Storage: zarr, xarray, dask for chunked data handling

Build System

  • Package Manager: Uses uv for dependency management (preferred) or pip
  • Configuration: pyproject.toml with setuptools backend
  • Lock File: uv.lock for reproducible builds
  • Test Framework: cram (shell-based functional testing)
  • Linting: ruff for code quality

Coding Standards

Python Style

  • Follow PEP 8 conventions
  • Use type hints for function signatures (e.g., Optional[str], Path, etc.)
  • Use typing_extensions.Annotated for CLI argument annotations with typer
  • Prefer pathlib Path over string paths
  • Use f-strings for string formatting

Code Organization

geotessera/
├── __init__.py          # Package exports and version
├── core.py              # Main GeoTessera class
├── registry.py          # Parquet registry management
├── cli.py               # Main CLI commands
├── registry_cli.py      # Registry-specific CLI
├── store.py             # Zarr v3 store access (GeoTesseraZarr)
├── tiles.py             # Tile abstraction (GeoTIFF + NPY)
├── visualization.py     # Visualization functions
├── web.py              # Web map generation
├── country.py          # Country bounding box utilities
└── progress.py         # Progress tracking utilities

Read the full file on GitHub · 254 lines

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. 5d ago First seen · 254 lines · 2,084 tokens per session scan A f6a35a3eb28d

Subscribe to this mod's changes

geotessera copilot-instructions.md is an instructions file published in the GitHub repository ucam-eo/geotessera (342 stars, last pushed today), licensed MIT. It adds 2,084 tokens to every session, about $0.0104 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.

Related

Other instructions, from other repositories