ha-helper-scaffold

ha-helper-scaffold is a skill for Claude Code from nolte/claude-home-assistant. It costs 207 tokens per session (2,018 once invoked), scanned A, original, MIT.

A Home Assistant skill that creates one stateful helper entity from a plain-language description. Home Assistant is software for automating and monitoring devices in a home.

In plain words
What is it for?
It scaffolds helpers such as switches, buttons, dates and times, numbers, dropdowns, text fields, counters, timers, and schedules.
Why use it?
It helps choose the appropriate helper type and produces the required YAML configuration instead of making you design the block manually.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-home-assistant plugin — 45 skills, 11 agents shipped together

Good fit It scaffolds helpers such as switches, buttons, dates and times, numbers, dropdowns, text fields, counters, timers, and schedules.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nolte/claude-home-assistant/ha-helper-scaffold
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-helper-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.

agentmods badge for ha-helper-scaffold

README.md
[![agentmods](https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-helper-scaffold/github.svg)](https://agentmods.dev/skills/nolte/claude-home-assistant/ha-helper-scaffold)
Your own site
<a href="https://agentmods.dev/skills/nolte/claude-home-assistant/ha-helper-scaffold"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-helper-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.

agentmods 80×15 button for ha-helper-scaffold

Your own site · 80×15
<a href="https://agentmods.dev/skills/nolte/claude-home-assistant/ha-helper-scaffold"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-helper-scaffold.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 207 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,018 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00207 $0.02018
Opus 5 $0.00103 $0.01009
Sonnet 5 $0.00041 $0.00404
Haiku 4.5 $0.00021 $0.00202

Measured 11d ago against content hash 642a9610f843, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ha-helper-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 11d 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-helper-scaffold/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HA Helper Scaffold

Spec: spec/claude/ha-helper-scaffold/en.md (EN canonical) / spec/claude/ha-helper-scaffold/de.md (DE translation).

Why this is a skill, not an agent

  • Human-visible scaffolding surface — the user describes what state they need held and reads back the YAML block plus the helper's read/mutate surface; a skill keeps this on the visible command surface, like the sibling scaffold skills.
  • Mid-flow interactivity — helper-type confirmation and the measured-value redirect are per-run dialogues the user approves before scaffolding.
  • Bounded, inline generation — a single helper block is small enough to generate inline; no isolated agent context is needed.
  • Counter-dimension considered: a one-shot generator could be an agent, but the type decision and the reported surface belong in the user's working context; skill wins.

When this skill activates

Use this skill to scaffold one stateful helper entity from a described intent: input_boolean, input_button, input_datetime, input_number, input_select, input_text, counter, timer, or schedule.

When NOT to activate

  • an automation, script, scene, template entity, or command integration → ha-automation-author
  • a derived/statistical helper sensor (bayesian, derivative, … utility_meter, group) → ha-derived-sensor-author
  • a measured value from real hardware → belongs in an integration, not an input helper
  • a blueprint → ha-blueprint-scaffold
  • deploying/importing into a running HA instance → out of scope

Hard rules

  1. One helper, one type, one run. No multi-helper batches.
  2. Intent is mandatory. Without it there is no scaffold; optional fields fall back to documented defaults stated in the output.
  3. Read the topic spec first. Read the matching ha-automation/<topic> spec before scaffolding.
  4. Right helper, not the convenient one. If the intent targets a measured value (→ sensor/integration), a derived value (→ ha-derived-sensor-author), or behavior another helper carries better (one-shot press → input_button, not input_boolean), redirect instead of scaffolding the wrong helper.
  5. Never overwrite an existing helper with the same object_id. Abort with the id quoted.
  6. Mandatory fields are mandatory. input_numbermin+max; input_select → non-empty options; input_datetime → at least one of has_date/has_time; input_textmax ≤ 255; timerrestore: true when it must survive a restart; schedule → per-weekday from/to windows. Set initial only for a fixed start value, else document restore semantics.
  7. Name per spec/ha/naming-conventions/en.md. object_id snake_case; English display names ≤ 50 chars.
  8. Verify HA internals against the official docs — don't reproduce schemas from memory (see spec/ha/upstream-docs-verification/en.md).

Read the full file on GitHub · 119 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. 11d ago First seen · 119 lines · 207 tokens per session scan A 642a9610f843

Subscribe to this mod's changes

ha-helper-scaffold is a skill published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 207 tokens to every session and 2,018 once invoked, about $0.0010 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.

Related

Other skills, from other repositories

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