agentmods.dev

ratebook: Instructions file for Claude Code

CLAUDE.md

ratebook CLAUDE.md is an instructions file for Claude Code from cbetz/ratebook. It costs 897 tokens per session, scanned A, original, Apache-2.0.

A set of instructions for contributing to Ratebook, an open project that calculates US electricity costs and provides those calculations to apps and AI agents. It also explains the project's Python and JavaScript package layout and data sources.

In plain words
What is it for?
Working on electricity-tariff data, bill and charging-window calculations, the MCP server, or related integrations in the repository.
Why use it?
It gives contributors and coding agents the repository structure, development conventions, and purpose of each package in one place.

Instructions file for Claude Code

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

This is cbetz/ratebook's own configuration. It tells Claude Code how to work on ratebook 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 ratebook configures →

not rated 1repo 2mo ago A scan 897 tokens original Apache-2.0
View source ↗ cbetz/ratebook
Reuse

Borrowing it

Nothing to install: this file belongs to cbetz/ratebook. 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/cbetz/ratebook/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/cbetz/ratebook

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 ratebook CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cbetz/ratebook/claude-md.svg)](https://agentmods.dev/instructions/cbetz/ratebook/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cbetz/ratebook/claude-md"><img src="https://agentmods.dev/badge/instructions/cbetz/ratebook/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 897 This file is loaded in full into every session.
When invoked 897 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 $0.00897 $0.00897
Opus 5 $0.00449 $0.00449
Sonnet 5 $0.00179 $0.00179
Haiku 4.5 $0.00090 $0.00090

Measured 7d ago against content hash 05b1d4a2fcd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ratebook 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 7d 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 · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ratebook — contributor & agent guide

The open rate engine for the electrified home: an openly licensed database of US electricity tariffs (parsed from utility PDFs by eval-harnessed LLM pipelines), a deterministic rate-calculation engine, and an MCP server — so any app, device, or agent can answer "what will this kWh cost me, and when should I charge?"

Status: pre-release. See docs/ROADMAP.md for what's shipped and what's next.

Repository layout (uv + pnpm monorepo)

  • packages/ratebook — the rate engine. Pure, deterministic functions over a Tariff data model (estimate_bill, estimate_annual, cheapest_charge_window, supported). No I/O.
  • packages/ratebook-data — the data plant: URDB loader, the LLM extraction pipeline (extract.py), and the golden-set scorecard (golden.py).
  • packages/ratebook-mcp — the MCP server exposing lookup_tariff, estimate_bill, compare_plans, best_charge_window over the corpus + engine.
  • packages/ratebook-ts — the TypeScript engine port (@ratebook/engine), kept in lockstep with the Python engine via shared JSON test vectors.
  • packages/ratebook-homeassistant — a Home Assistant custom integration (electricity-price + cheapest-charge-window sensors) over the engine.

Development

uv sync                    # install all workspace packages + dev tools
uv run pytest              # Python tests
uv run ruff check .        # lint
uv run ratebook-data urdb  # download URDB bulk CSV → data/raw/, load into data/ratebook.duckdb
uv run ratebook-mcp        # run the MCP server (stdio)

pnpm -C packages/ratebook-ts install && pnpm -C packages/ratebook-ts test   # TS engine + vectors

LLM extraction (ratebook-data's extract extra) additionally needs the anthropic SDK and an API key; the engine, MCP, and HA paths never require it.

Conventions

  • Python 3.12+, uv workspace, pytest (+ hypothesis for the engine's property tests), ruff. TypeScript: pnpm, vitest.
  • The rate engine is pure functions, deterministic, boring, and bulletproof. Correctness bugs here are customer-facing "your app lied about my bill" failures — every change is property-tested and the engine is cross-validated against NREL's PySAM utilityrate5.
  • The two engines must never diverge. Both reproduce packages/ratebook/tests/vectors/v0_bills.json byte-for-byte; regenerate with uv run python packages/ratebook/tests/generate_vectors.py.
  • Honesty about uncertainty is the brand. Every record should carry its source PDF URL, effective date, extraction confidence, and last-verified date. Never claim coverage or accuracy that hasn't been eval'd; "unknown" is a first-class answer. The accuracy scorecard is published content, not a marketing surface.
  • Keep docs/ROADMAP.md current at the end of each working session: what shipped, what's next, open questions.

Read the full file on GitHub · 68 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. 7d ago First seen · 68 lines · 897 tokens per session scan A 05b1d4a2fcd0

Subscribe to this mod's changes

ratebook CLAUDE.md is an instructions file published in the GitHub repository cbetz/ratebook (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 897 tokens to every session, about $0.0045 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.

Data and AIFinance and fintechduckdbelectricityenergyev-charginghacshome-assistant
Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

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 · 6,785 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 · 7,296 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 · 4,469 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens