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 agentmods add instructions/boettiger-lab/data-workflows/copilot-instructionsgit clone --depth 1 https://github.com/boettiger-lab/data-workflowsWhat 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 | $0.00455 | $0.00455 |
| Opus 5 | $0.00228 | $0.00228 |
| Sonnet 5 | $0.00091 | $0.00091 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
data-workflows 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 2d 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.
What it actually says
Start Here
Read AGENTS.md before doing anything. It explains the workflow for processing datasets.
This repo has no source code. Do not look for Python modules to study. The cng-datasets CLI is installed via pip and used as a black box — see its README for CLI docs.
Repository Structure
AGENTS.md— complete instructions for processing datasetsDATASET_DOCUMENTATION_WORKFLOW.md— how to create STAC metadata after processingtodo.md— dataset completion trackercatalog/— per-dataset configs: k8s YAML, STAC metadata, processing notes
Local Environment
The cng-datasets CLI is used to generate k8s job YAML files (not for processing data locally).
Setup:
uv venv
source .venv/bin/activate
uv pip install git+https://github.com/boettiger-lab/datasets.git
Do not run data processing commands (vector, raster, repartition) locally — those run inside k8s pods.
Available Skills
Detailed reference guides are in .claude/skills/. Do not read these proactively — load a skill only when the task requires it:
| Skill file | When to load |
|---|---|
.claude/skills/stac-authoring/SKILL.md |
Writing or editing any stac-collection.json or dataset README |
.claude/skills/raster-hexing/SKILL.md |
Ingesting or re-hexing a GeoTIFF/COG — resolution, reducer, mosaicking |
.claude/skills/hex-tuning/SKILL.md |
A hex job OOMs, or choosing native/parent H3 resolutions and chunk sizes |
.claude/skills/job-troubleshooting/SKILL.md |
A job fails, hangs, or a published parquet will not read |
.claude/skills/dataset-recipes/SKILL.md |
Starting an ingest that resembles a worked example |
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.
- 2d ago First seen · 38 lines · 455 tokens per session scan A 932fdcc07c23
data-workflows copilot-instructions.md is an instructions file published in the GitHub repository boettiger-lab/data-workflows (5 stars, last pushed 2d ago), licensed BSD-3-Clause. It adds 455 tokens to every session, about $0.0023 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 2026-08-31.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.