What is ha-esphome-config-scaffold?

A guide for creating one ESPHome device configuration in YAML. ESPHome is software that turns supported microcontrollers into smart-home devices.

Use it to scaffold a new device file with shared configuration, Wi-Fi fallback, a device-specific API key, protected updates, and initial platform blocks.

It provides a defined starting structure for device naming, Wi-Fi, encryption, updates, logging, and initial sensors or controls.

ha-esphome-config-scaffold — Skill for Claude Code by nolte

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.

Any agent

npx skills add nolte/claude-home-assistant --skill ha-esphome-config-scaffold

Clone the repo

git clone --depth 1 https://github.com/nolte/claude-home-assistant

Made for: Claude Code.

Or install claude-home-assistant, the plugin that ships this one along with the rest of its 45 skills, 11 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-esphome-config-scaffold/github.svg)](https://agentmods.dev/skills/nolte/claude-home-assistant/ha-esphome-config-scaffold)

Your own site

<a href="https://agentmods.dev/skills/nolte/claude-home-assistant/ha-esphome-config-scaffold"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-esphome-config-scaffold/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nolte/claude-home-assistant/ha-esphome-config-scaffold"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-esphome-config-scaffold.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 220 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,771 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00220	$0.01771
Opus 5	$0.00110	$0.00886
Sonnet 5	$0.00044	$0.00354
Haiku 4.5	$0.00022	$0.00177

Measured 12d ago against content hash 6ff12f4de251, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ha-esphome-config-scaffold 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 12d 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.

skills/ha-esphome-config-scaffold/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HA ESPHome Config Scaffold

Spec: spec/claude/ha-esphome-config-scaffold/en.md (EN canonical) / spec/claude/ha-esphome-config-scaffold/de.md (DE translation). Grounding spec: spec/ha/esphome-config-patterns/en.md.

Scaffolds exactly one new ESPHome device-config YAML per invocation, in the consumer repository's device-config root, conforming to every MUST in the grounding spec.

Why this is a skill, not an agent

Mid-flow approval is the contract (decisive): device name, board family, shared-concern set, and the initial platform list are elicited and confirmed with the operator before any file exists; a fire-and-forget agent would guess where the spec demands answers.
Quick, targeted change: one new YAML file in the repository the conversation is scoped to — main-conversation territory per the change-scope dimension.
Counter-dimension considered: the boilerplate composition is template-like and self-contained (agent bias), but the scaffold is the first step of device work the conversation continues, so a report boundary would only add friction.

When this skill activates

The user asks for a new ESPHome device config — "scaffold an ESPHome config for a soil-moisture node", "neues ESPHome-Gerät anlegen" — in a repository that holds ESPHome device YAML (fixture layout: src/*.yaml).

When NOT to activate

extending an existing device file (new sensor, bus, component) → ha-esphome-config-augment
the repository layout, the common/ tree, or the shared packages themselves → ha-esphome-fleet-scaffold / ha-esphome-package-author
authoring an ESPHome custom component (C++/Python) → out of scope; no component axis exists yet
a Home Assistant Custom Integration → ha-integration-scaffold
compiling, flashing, or deploying → the ESPHome toolchain / operator, never this skill

Hard rules

Read spec/ha/esphome-config-patterns/en.md first. Do not generate from memory.
Verify every schema key against the official ESPHome docs (https://esphome.io) per spec/ha/upstream-docs-verification — components, platforms, and their keys change between releases.
No literal credentials, ever. wifi, api encryption, and ota resolve from environment variables (!env_var), never from !secret and never from a literal — the portfolio's credential mechanism per the grounding spec, chosen because it reaches a local build and a CI build alike and works in packages where !secret provably cannot. The api encryption key is per device: the device file sets api_key: !env_var <DEVICE>_API_KEY and the shared package consumes ${api_key}. Report every variable the operator must set.
packages: for shared blocks. Never introduce <<: !include merge keys in a new file; reuse existing shared files where they fit, propose a new concern-scoped one when none does.
Substitution-driven naming. name / friendly_name declared once; every entity name derives from ${friendly_name} per the spec's naming rule.
One device, one file. No multi-device batches; no edits to other device files.
No deploy. The skill ends at the written file plus the validation step report.

Read the full file on GitHub · 92 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.

12d ago First seen · 92 lines · 220 tokens per session scan A 6ff12f4de251

Subscribe to this mod's changes

ha-esphome-config-scaffold is a skill published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 220 tokens to every session and 1,771 once invoked, about $0.0011 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.

Claude Code Hardware and IoT agents anthropic automation blueprints claude esphome home-assistant scaffolding yaml

embedded-iot

Embedded systems firmware, microcontrollers (ESP32, STM32, Arduino, Raspberry Pi), RTOS (FreeRTOS, Zephyr), IoT protocols (MQTT, CoAP, BLE), bare-metal C/C++, and hardware peripheral interfaces (I2C, SPI, UART, GPIO). Use when developing firmware, working with microcontrollers, or building IoT devices.

travisjneuman/.claude · 80 tokens

spark-environment-setup

Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.

wshobson/agents · 76 tokens

spark-training-gotchas

Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.

wshobson/agents · 63 tokens

security-compliance

Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.

sangrokjung/claude-forge · 56 tokens

stride-analysis-patterns

Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.

sangrokjung/claude-forge · 30 tokens

review-loop

Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…

sangrokjung/claude-forge · 100 tokens