agentmods.dev

aquascope: Instructions file for Claude Code

CLAUDE.md

aquascope CLAUDE.md is an instructions file for Claude Code from Rekin226/aquascope. It costs 2,874 tokens per session, scanned A, original, MIT.

A repository guide for a coding agent working on AquaScope, a Python water-data and hydrology project with a web app, command-line tools, and shared code. It explains the project layout, setup, and checks that local changes must pass.

In plain words
What is it for?
Use it when changing AquaScope code to find the right component, understand how its interfaces fit together, and run the required local checks.
Why use it?
It gives the agent the project’s design rules before it edits files, reducing changes that put logic in the wrong layer or fail the repository’s checks.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is Rekin226/aquascope's own configuration. It tells Claude Code how to work on aquascope itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything aquascope configures →

not rated 31repo +1 changed 17d ago A scan 2,874 tokens original MIT
View source ↗ Rekin226/aquascope rekin226-aquascope-explorer.static.hf.space
Reuse

Borrowing it

Nothing to install: this file belongs to Rekin226/aquascope. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Rekin226/aquascope/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Rekin226/aquascope

Made for: Claude Code.

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 aquascope CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rekin226/aquascope/claude-md/github.svg)](https://agentmods.dev/instructions/rekin226/aquascope/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rekin226/aquascope/claude-md"><img src="https://agentmods.dev/badge/instructions/rekin226/aquascope/claude-md/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 aquascope CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rekin226/aquascope/claude-md"><img src="https://agentmods.dev/badge/instructions/rekin226/aquascope/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,874 This file is loaded in full into every session.
When invoked 2,874 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.02874 $0.02874
Opus 5.5 $0.01150 $0.01150
Sonnet 5.5 $0.00575 $0.00575
Haiku 4.5 $0.00287 $0.00287

Measured 17d ago against content hash 2e3a8eab4216, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aquascope CLAUDE.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 17d 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.

CLAUDE.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AquaScope, for Claude

Read this before changing anything. It is the short version of how this repo is put together and what CI will fail you on. CONTRIBUTING.md is the contributor-facing version with more hand-holding.

What this is

A Python library for water data and hydrology, and a platform built on top of it:

  1. The Archive (aquascope/archive/): every station catalog as GeoParquet plus daily observations, published to the Hugging Face dataset Rekin226/aquascope-gauges and rebuilt weekly by CI.
  2. The Explorer (explorer/): a static web app (MapLibre + DuckDB-WASM + Pyodide) that runs the library in the browser. No server, no install.
  3. The Analyst: aquascope ask, aquascope mcp, aquascope ingest.
  4. Ecosystem: the GeoLibre plugin in integrations/, docs, the data paper.

The one rule: one engine, three faces

Every capability is a plain Python function (inputs) -> dict in the package. The web app, the MCP server and the CLI are thin faces over the same functions. aquascope/explore.py, aquascope/workbench.py and aquascope/mcp_server.py are where those functions live.

So: implement in the package first, then expose. Logic written inside explorer/*.js, inside a Streamlit page, or inside a CLI handler is going the wrong way and will be asked to move. This is the rule that stops the platform forking again; it already did once, when the Explorer and the Streamlit dashboard ended up sharing nothing but the package name.

Layout

aquascope/
  collectors/      one file per data source, subclassing BaseCollector
  schemas/         Pydantic records: water_data.py, groundwater.py, climate.py,
                   agriculture.py, station.py
  registry.py      SOURCES: the single source of truth about every collector
  archive/         the harvester behind the Hugging Face dataset
  explore.py       station/point analysis used by the Explorer and the Analyst
  workbench.py     the analyses shared by every face (the `TOOLS` table)
  mcp_server.py    `aquascope mcp`
  ai_engine/       the Analyst tool loop (analyst.py) and the recommender
  hydrology/ groundwater/ agri/ climate/ spatial/ analysis/ models/
  io/interop.py    records to xarray/pandas
  ingest.py study.py gym/ maintenance/ pipelines/ reporting/ alerts/
  dashboard/       Streamlit, local only (the public deployments were retired)
  cli.py           every verb
explorer/          the static web app (see below)
integrations/      the GeoLibre plugin
tests/             mirrors the package layout
docs/              MkDocs site; docs/data_sources.md holds the sources table

Read the full file on GitHub · 220 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. 17d ago Changed · +3 lines · +82 tokens per session 2e3a8eab4216
  2. 26d ago Changed · +2 lines · +34 tokens per session 2400849dbf50
  3. 1mo ago First seen · 215 lines · 2,758 tokens per session scan A 3d1432103ccf

Subscribe to this mod's changes

aquascope CLAUDE.md is an instructions file published in the GitHub repository Rekin226/aquascope (31 stars, last pushed yesterday), licensed MIT. It adds 2,874 tokens to every session, about $0.0115 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 2026-09-16.

HydrologyPythonWriting and docsaienvironmental-scienceopen-datausgs
Related

Other instructions, from other repositories

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).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens