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/dcb/homeassistant-claude-kit/agents-mdgit clone --depth 1 https://github.com/dcb/homeassistant-claude-kitWrote 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.
[](https://agentmods.dev/instructions/dcb/homeassistant-claude-kit/agents-md)<a href="https://agentmods.dev/instructions/dcb/homeassistant-claude-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/dcb/homeassistant-claude-kit/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00994 | $0.00994 |
| Opus 5 | $0.00497 | $0.00497 |
| Sonnet 5 | $0.00199 | $0.00199 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
homeassistant-claude-kit 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Conventions
Tool-agnostic conventions for AI coding assistants (Cursor, GitHub Copilot, Windsurf, etc.). If you are Claude Code, follow CLAUDE.md instead — it has additional hook and permission configuration.
Core Principles
-
Read before writing. Before touching any file, read it. Before using an entity ID, verify it exists via
make entitiesordocs/system-*.md. Never guess. -
Validate before deploying. Always run
make validatebeforemake push. The pre-push hook enforces this, but you should validate proactively after edits. -
Document every change. After pushing changes, update the relevant
docs/system-*.mdfile. No automation or helper should be undocumented. -
Ask when uncertain. Entity IDs, device behavior, household schedules, and user preferences require runtime knowledge. Ask rather than assume.
Boundaries
Always Do
- Read
docs/system-*.mdfor the relevant domain before modifying automations - Read
docs/house-rules.mdbefore adding automations that affect routines. If the file is inaccessible (privacy mode), ask the user for relevant constraints. - Run
make validateafter editing any YAML inconfig/ - Reload the relevant domain after
make push(automation/reload,script/reload, etc.) - Update
docs/system-*.mdafter any configuration change
Ask First
- Creating new
input_number,input_boolean, orinput_selecthelpers - Adding automations that interact with existing ones
- Changing
configuration.yaml(requires HA restart, not just reload) - Deleting or renaming automations, scripts, or helpers
Never Do
- Modify files in
config/.storage/— these are managed by HA at runtime - Hardcode thresholds, timeouts, or temperatures — use
input_*helpers - Use
continue_on_error: trueto silence failures - Guess entity IDs — always verify
- Push without validating
File Editing Rules
- YAML files in
config/are safe to edit locally and push withmake push .storage/files must only be changed through the HA UI- Dashboard files (
dashboard/src/) are safe to edit; runmake deploy-dashboardto deploy
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.
- 4d ago First seen · 77 lines · 994 tokens per session scan A f66f1043b7fe
homeassistant-claude-kit AGENTS.md is an instructions file published in the GitHub repository dcb/homeassistant-claude-kit (119 stars, last pushed 6d ago), licensed MIT. It adds 994 tokens to every session, about $0.0050 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 2026-08-30.
Other instructions, from other repositories
firmware CLAUDE.md
Claude Code instructions for OpenIPC/firmware, covering claude.md, what this is, before you start: is this the right repository?, build and common tasks.
Tutorial_AwesomeModernCPP AGENTS.md
AGENTS.md instructions for Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP, covering agents.md, 这是什么, 通用 essentials(所有 agent 必读) and 你来做什么?(按场景路由).
brilliant_sdk AGENTS.md
Instructions for brilliantlabsAR/brilliant_sdk, covering brilliant sdk — agent guide, how an app works (the pattern behind everything), minimal reading paths, verify without hardware and testing.
NeoMind CLAUDE.md
Claude Code instructions for camthink-ai/NeoMind, covering neomind — edge ai platform for iot, development commands, ecosystem repositories, extension package contract (.nep) and device type template contract (json).
zmk-config AGENTS.md
AGENTS.md instructions for urob/zmk-config, covering customization guide, ground rules, how the multi-board layout works, adding a new board and where to change what.
ext-apps CLAUDE.md
Claude Code instructions for modelcontextprotocol/ext-apps, a project described as: Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP servers.