What is ha-derived-sensor-author?

A Home Assistant helper sensor that calculates a new value from other sensor data, such as an average, rate of change, threshold, trend, or total. It produces the configuration as a YAML block.

Use it to create one derived or statistical sensor from a plain-language description, such as a smoothed reading, usage total, time-based statistic, or utility meter.

It removes the need to choose and format the right built-in calculation manually. It also checks that the block follows the relevant Home Assistant specification.

ha-derived-sensor-author — 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-derived-sensor-author

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-derived-sensor-author/github.svg)](https://agentmods.dev/skills/nolte/claude-home-assistant/ha-derived-sensor-author)

Your own site

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

Per session 217 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,290 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	$0.00217	$0.02290
Opus 5	$0.00109	$0.01145
Sonnet 5	$0.00043	$0.00458
Haiku 4.5	$0.00022	$0.00229

Measured 12d ago against content hash f0c8fa49a813, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ha-derived-sensor-author 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-derived-sensor-author/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HA Derived Sensor Author

Spec: spec/claude/ha-derived-sensor-author/en.md (EN canonical) / spec/claude/ha-derived-sensor-author/de.md (DE translation).

Why this is a skill, not an agent

Human-visible authoring surface — the user describes the derived value they need and reads back the YAML and the conformance report; a skill keeps this on the visible command surface, like the sibling author/scaffold skills.
Mid-flow interactivity — integration selection and the delimitation redirect (rate vs. smoothing vs. integral; threshold vs. trend) are per-run dialogues the user approves before generation.
Bounded, inline generation — a single sensor block is small enough to generate inline.
Counter-dimension considered: the draft→validate loop could be an agent, but the integration choice and the runtime-dependency notes belong in the user's working context; skill wins.

When this skill activates

Use this skill to author one derived/statistical helper sensor from a described intent: bayesian, derivative, filter, min_max, statistics, threshold, trend, history_stats, integration (Riemann), utility_meter, or group.

When NOT to activate

the generic template: integration (free-form Jinja sensors) → ha-automation-author
a stateful helper (input_*, counter, timer, schedule) → ha-helper-scaffold
an automation, script, or scene → ha-automation-author
a real sensor from your own integration → ha-integration-scaffold
a blueprint → ha-blueprint-scaffold
deploying/importing into a running HA instance → out of scope

Hard rules

One sensor, one integration, one run. No batches.
Intent is mandatory. Optional fields fall back to documented defaults stated in the output.
Read the topic spec first. Read the matching ha-automation/<topic> spec before generating.
Right integration, with delimitation. Rate → derivative, smoothing → filter, time-integral → integration; momentary aggregate → min_max, time aggregate → statistics, past-window → history_stats; momentary threshold → threshold, direction → trend. A free formula → template (via ha-automation-author); a stored value → ha-helper-scaffold. Redirect rather than forcing the wrong one.
A source entity is required for every integration except bayesian (which works off observations). No source → ask, don't guess.
Set the math-bearing parameter correctly per the topic spec — never prob_given_* of 0/1; unit_time deliberate; derivative on a non-negative source needs state_class: total_increasing; filter window_size not a needlessly large integer; min_max sources share one unit; statistics state_characteristic matches source type; threshold lower < upper with hysteresis on noisy sources; trend min_gradient in units per second; history_stats exactly two of start/end/duration; utility_meter a monotonic source with cycle or cron (not both); group modern per-domain, deliberate all.
Type the sensor and guard the source. Correct sensor/binary_sensor, device_class/state_class; robust against source unavailable/unknown. Name per spec/ha/naming-conventions/en.md.
Never overwrite an existing sensor with the same unique_id. Verify HA internals against the official docs (see spec/ha/upstream-docs-verification/en.md).

Read the full file on GitHub · 121 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 · 121 lines · 217 tokens per session scan A f0c8fa49a813

Subscribe to this mod's changes

ha-derived-sensor-author is a skill published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 217 tokens to every session and 2,290 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 home-assistant sensor statistics 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