openelectricity AGENTS.md

openelectricity AGENTS.md is an instructions file for Codex, OpenCode from opennem/openelectricity. It costs 885 tokens per session, scanned A, original, MIT.

Project instructions for Open Electricity, covering how contributors should start work, run the project, verify changes, and follow repository rules.

In plain words
What is it for?
Use them when contributing to the Open Electricity repository. They guide setup with pnpm, development commands, architecture reading, focused changes, language style, and Git safety.
Why use it?
They provide the project-specific context and safety rules needed before changing unfamiliar code, including which documentation and personal notes to read.

Instructions file for CodexOpenCode

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/opennem/openelectricity/agents-md
Clone the repo
git clone --depth 1 https://github.com/opennem/openelectricity

Made for: Codex, OpenCode.

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 openelectricity AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/opennem/openelectricity/agents-md.svg)](https://agentmods.dev/instructions/opennem/openelectricity/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/opennem/openelectricity/agents-md"><img src="https://agentmods.dev/badge/instructions/opennem/openelectricity/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 885 This file is loaded in full into every session.
When invoked 885 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 $0.00885 $0.00885
Opus 5 $0.00443 $0.00443
Sonnet 5 $0.00177 $0.00177
Haiku 4.5 $0.00089 $0.00089

Measured 5d ago against content hash 9db719655b2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

openelectricity AGENTS.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.

AGENTS.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Open Electricity agent guide

This is the canonical guidance for any coding agent working in this repository. Platform-specific instruction files must defer to this document rather than duplicating it.

Start here

  • If personal-notes/ exists, begin with personal-notes/PLAN.md and personal-notes/TODO.md for the maintainer's current priorities and local working context. The directory is intentionally gitignored and may be absent.
  • Keep all project-specific agent memory, next actions, TODOs, and planning notes in personal-notes/. Do not create local planning or memory files elsewhere in the repository.
  • Read README.md for setup and docs/architecture.md before unfamiliar work.
  • Preserve unrelated working-tree changes. Do not reset, reformat, or stage them.
  • Prefer small, focused changes. Read the nearby code and tests before changing a subsystem.
  • Use UK English in user-facing copy, documentation, and commit messages.

Commands and verification

  • Use pnpm only. Node 22.12 or later is required.
  • pnpm run dev is the contributor path and reads .env.
  • pnpm run doppler-dev is a maintainer convenience; never make Doppler a requirement for contributors.
  • Run pnpm run test:unit for code changes. Run the narrowest relevant test first when practical.
  • Run pnpm run check after JavaScript, TypeScript, or Svelte changes. It has a known pre-existing error baseline; do not introduce errors in files you touch.
  • Run pnpm run lint when formatting or linting is relevant. Do not run pnpm run format over unrelated files without permission.

Project rules

  • This is Svelte 5 and SvelteKit. Use runes in new reactive code and property event handlers such as onclick, not legacy on:click syntax.
  • Do not introduce React-bound packages. Install framework-neutral packages only, and add every package with pnpm add -D.
  • Keep contributor .env support. When adding an environment variable, update .env.example and explain both local .env and maintainer Doppler flows in any setup documentation you change.
  • Avoid new public /api/* routes for server-only data calls; call the service directly from a server load function instead. New client-facing endpoints need validation, caching, error handling, and a documented browser caller.
  • Tests live next to the code they cover: thing.js and thing.test.js, never in a new __tests__/ directory.
  • Generated facility OG cards are committed assets. Follow the root README's build:og instructions; do not regenerate them incidentally.

Read the full file on GitHub · 72 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 · 72 lines · 885 tokens per session scan A 9db719655b2f

Subscribe to this mod's changes

openelectricity AGENTS.md is an instructions file published in the GitHub repository opennem/openelectricity (10 stars, last pushed 5d ago), licensed MIT. It adds 885 tokens to every session, about $0.0044 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.