Borrowing it
Nothing to install: this file belongs to nolte/claude-home-assistant. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nolte/claude-home-assistant/develop/CLAUDE.mdgit clone --depth 1 https://github.com/nolte/claude-home-assistantWrote 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/nolte/claude-home-assistant/claude-md)<a href="https://agentmods.dev/instructions/nolte/claude-home-assistant/claude-md"><img src="https://agentmods.dev/badge/instructions/nolte/claude-home-assistant/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/nolte/claude-home-assistant/claude-md"><img src="https://agentmods.dev/badge/instructions/nolte/claude-home-assistant/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00657 | $0.00657 |
| Opus 5 | $0.00329 | $0.00329 |
| Sonnet 5 | $0.00131 | $0.00131 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
claude-home-assistant 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 8d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Orientation for Claude Code and contributors working inside this repository.
What this repo is
claude-home-assistant is a Claude Code plugin that bundles skills, agents, and specifications for efficient development of Home Assistant artifacts — custom integrations (Python), Lovelace cards (TypeScript / JavaScript), blueprints and automations (YAML), and ESPHome / add-on work.
Layout
.claude-plugin/plugin.json— plugin manifest (name, version, author).claude-plugin/marketplace.json— marketplace catalog (downstream install source)skills/<name>/SKILL.md— reusable skills; each folder is one skillagents/<name>.md— reusable sub-agents (when present)spec/— bilingual specifications (EN canonical, DE translation)docs/— MkDocs source (bilingual once content lands; DE-first)tests/— repo-local test harness (placeholder until first runtime check exists)
Plugin skills are namespaced by plugin name — for example /claude-home-assistant:<skill>.
Command entry points
Local automation runs through Taskfile.yml:
task lint— pre-commit checkstask test— test suite (placeholder — no runtime tests yet)task docs— build the MkDocs sitetask plugin:reload— launch Claude Code with this repo loaded as a plugin (dogfooding)
Dogfooding
When developing inside this repository, launch Claude Code with the plugin pointed at the repo root:
claude --plugin-dir .
Use /reload-plugins inside the session to pick up changes without restarting.
Conventions
- New skills are scaffolded via
/nolte-shared:skill-management. - Specs are authored and translated via
/nolte-shared:spec. - Project-structure drift is checked via
/nolte-shared:project-structure-apply. - Pull requests are created via
/nolte-shared:pull-request-create.
Authoring rules
- Keep
CLAUDE.md,spec/, and the plugin manifest in sync with what the repo actually ships. - Verify uncertainties against the official Home Assistant docs before asserting or generating any HA fact — Developer docs
home-assistant/developers.home-assistantfor integration internals, config flow, entities, coordinators, quality scale, and frontend/WebSocket contracts; architecture/user docshome-assistant/home-assistant.iofor architecture, blueprints, and YAML schemas. Don't answer HA-internal questions from memory. Normative spec:spec/ha/upstream-docs-verification. - Never copy plugin-owned skills into a consumer's
.claude/skills/— distribution happens via the plugin marketplace. - All generated configuration files (
.github/*.yml,Taskfile.yml, workflow YAML) are written in English for portfolio consistency, regardless of the language used in conversation.
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.
- 8d ago First seen · 53 lines · 657 tokens per session scan A 89f39eeb9cc9
claude-home-assistant CLAUDE.md is an instructions file published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 657 tokens to every session, about $0.0033 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
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.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.