agentmods.dev

core AGENTS.md

A set of repository instructions for Home Assistant Core, the Python-based home-automation application. It covers GitHub Copilot and Claude Code, commits, pull requests, setup, testing, and Python syntax.

In plain words
What is it for?
Use it when setting up the development environment or making, testing, committing, and submitting changes to Home Assistant Core.
Why use it?
It records project-specific rules and commands that are easy to miss when working in an unfamiliar repository.

Instructions file for CodexOpenCode

90k yesterday C scan 1,150 tokens copy · 86% Apache-2.0
View the source file home-assistant/core
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/home-assistant/core/agents-md
Clone the repo
git clone --depth 1 https://github.com/home-assistant/core

Made for: Codex, OpenCode.

Per session 1,150 This file is loaded in full into every session.
When invoked 1,150 The same file — it is already loaded in full.
Security scan C 2 findings. Scan, not verified.
Origin 86% copy Near-identical to another mod 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 $0.01150 $0.01150
Opus 5 $0.00575 $0.00575
Sonnet 5 $0.00230 $0.00230
Haiku 4.5 $0.00115 $0.00115

Measured yesterday against content hash 571e48dec157, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

core AGENTS.md scanned grade C with 2 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 yesterday.

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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- When entering a new environment or worktree, run `script/setup` to set up the virtual environment with all development dependencies (pylint, pre-commit hooks, etc.). This is required before committing. If uv reports th

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- When entering a new environment or worktree, run `script/setup` to set up the virtual environment with all development dependencies (pylint, pre-commit hooks, etc.). This is required before committing. If uv reports th
Origin

This is a copy

86% identical to core copilot-instructions.md — 137 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot & Claude Code Instructions

This repository contains the core of Home Assistant, a Python 3 based home automation application.

Git Commit Guidelines

  • Do NOT amend, squash, or rebase commits that have already been pushed to the PR branch after the PR is opened - Reviewers need to follow the commit history, as well as see what changed since their last review

Pull Requests

  • When opening a pull request, use the repository's PR template (.github/PULL_REQUEST_TEMPLATE.md). NEVER REMOVE ANYTHING from the template.
  • Do not remove checkboxes that are not checked — leave all unchecked checkboxes in place so reviewers can see which options were not selected.

Development Commands

  • Run "python3" in current virtual environment to ensure the correct Python version is used for testing.
  • When entering a new environment or worktree, run script/setup to set up the virtual environment with all development dependencies (pylint, pre-commit hooks, etc.). This is required before committing. If uv reports that no download was found for the required Python version, the environment is running an outdated version of uv; upgrade it with curl -LsSf https://astral.sh/uv/install.sh | sh and run script/setup again.
  • .vscode/tasks.json contains useful commands used for development.
  • After finishing a code session, run uv run --no-sync prek run --all-files to check for linting and formatting issues.

Python Syntax Notes

  • Home Assistant officially supports Python 3.14 as its minimum version. Do not flag syntax or features that require Python 3.14 as issues, and do not suggest workarounds for older Python versions.
  • Python 3.14 explicitly allows except TypeA, TypeB: without parentheses. Never flag this as an issue.
  • Python 3.14 evaluates annotations lazily (PEP 649). Forward references in annotations do not need to be quoted — annotations can reference names defined later in the module without quoting them or using from __future__ import annotations. Do not flag unquoted forward references in annotations as issues.

Read the full file on GitHub · 57 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. yesterday First seen · 57 lines · 1,150 tokens per session scan C 571e48dec157

Subscribe to this mod's changes

core AGENTS.md is an instructions file published in the GitHub repository home-assistant/core (90,198 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,150 tokens to every session, about $0.0057 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). It is 86% identical to core copilot-instructions.md, differing in 137 lines, and is treated as a copy.

Git and workflowLanguagesTestinghome-automationinternet-of-thingsiotmqttraspberry-pi
Related

Other instructions, from other repositories

Gladys AGENTS.md

AGENTS.md instructions for GladysAssistant/Gladys, covering agents.md, cursor cloud specific instructions, running the app (dev mode), non-obvious caveats and feature specs (spec-first process).

GladysAssistant/Gladys · 2,456 tokens

iot-dc3 AGENTS.md

AGENTS.md instructions for pnoker/iot-dc3, covering agents.md, scope and precedence, sources of truth, project overview and repository map.

pnoker/iot-dc3 · 4,985 tokens

iot-dc3 CLAUDE.md

Claude Code instructions for pnoker/iot-dc3: This file provides guidance to AI coding assistants when working with code in this repository.

pnoker/iot-dc3 · 80 tokens

AetherEdge AGENTS.md

Instructions for EvanL1/AetherEdge, covering aetheredge agent instructions, product direction, repository map, architecture boundaries and ai safety.

EvanL1/AetherEdge · 1,921 tokens

devices-mcp AGENTS.md

Instructions for sandraschi/devices-mcp, covering devices-mcp — per-repo agent instructions, what this repo is, git branches, startup and backend only (fastapi, port 10717).

sandraschi/devices-mcp · 1,198 tokens

devices-mcp CLAUDE.md

Instructions for sandraschi/devices-mcp, covering devices-mcp -- claude code guide, entry points, standards and ports.

sandraschi/devices-mcp · 200 tokens