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/home-assistant/core/integrationsgit clone --depth 1 https://github.com/home-assistant/coreWhat 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 | $0.00733 | $0.00733 |
| Opus 5 | $0.00367 | $0.00367 |
| Sonnet 5 | $0.00147 | $0.00147 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
core integrations.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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
File Locations
- Integration code:
./homeassistant/components/<integration_domain>/ - Integration tests:
./tests/components/<integration_domain>/
General guidelines
- When looking for examples, prefer integrations with the platinum or gold quality scale level first.
- Polling intervals are NOT user-configurable. Never add scan_interval, update_interval, or polling frequency options to config flows or config entries.
- Do NOT allow users to set config entry names in config flows. Names are automatically generated or can be customized later in UI. Exception: helper integrations may allow custom names.
- For entity actions and entity services, avoid requesting redundant defensive checks for fields already enforced by Home Assistant validation schemas and entity filters; only request extra guards when values bypass validation or are transformed unsafely.
- When validation guarantees a key is present, prefer direct dictionary indexing (
data["key"]) over.get("key")so invalid assumptions fail fast. - Integrations should be thin wrappers. Protocol parsing, device state machines, or other domain logic belong in a separate PyPI library, not in the integration itself. If unsure, ask before inlining.
- Integrations should not implement fixes or workarounds for limitations in libraries. Instead, the library should be updated to fix the issue.
The following platforms have extra guidelines:
- Diagnostics:
platform-diagnostics.mdfor diagnostic data collection - Repairs:
platform-repairs.mdfor user-actionable repair issues
Entity platforms
- Ensure
async_added_to_hass()andasync_will_remove_from_hass()have symmetrical behavior. For example, if a subscription is created inasync_added_to_hass(), it should be unsubscribed inasync_will_remove_from_hass(). Also, if something is torn down inasync_will_remove_from_hass(), it should be set up inasync_added_to_hass(). - Entity base class (e.g.
SensorEntity,TrackerEntity) provide a stable API for child classes to inherit from. Do not suggest redeclaring or duplicating attributes, properties, or methods the base class already provides, and do not add guards against the parent's behavior changing — rely on the base class instead.
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.
- today First seen · 52 lines · 733 tokens per session scan A 2f338b8f7e79
core integrations.instructions.md is an instructions file published in the GitHub repository home-assistant/core (90,198 stars, last pushed today), licensed Apache-2.0. It adds 733 tokens to every session, about $0.0037 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
Gladys 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).
meshcore-mqtt AGENTS.md
AGENTS.md instructions for ipnet-mesh/meshcore-mqtt, covering meshcore mqtt bridge - opencode context, instructions for opencode, project overview, key features and architecture.
meshcore-mqtt CLAUDE.md
Claude Code instructions for ipnet-mesh/meshcore-mqtt, a project described as: MeshCore MQTT Bridge (Companion App over Serial/BLE/TCP).
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.
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.
AetherEdge AGENTS.md
Instructions for EvanL1/AetherEdge, covering aetheredge agent instructions, product direction, repository map, architecture boundaries and ai safety.