What is ha-bluetooth-augment?

A Home Assistant integration update that adds Bluetooth support for discovering devices and receiving their broadcasts.

Use it to extend an existing Home Assistant custom integration with Bluetooth discovery, advertisement handling, and the related configuration and validation work.

It provides the required Bluetooth matching, scanning, callback, and coordinator wiring while making the passive-versus-connectable choice explicit.

ha-bluetooth-augment — 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-bluetooth-augment

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-bluetooth-augment/github.svg)](https://agentmods.dev/skills/nolte/claude-home-assistant/ha-bluetooth-augment)

Your own site

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

Per session 204 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,314 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	$0.00204	$0.02314
Opus 5	$0.00102	$0.01157
Sonnet 5	$0.00041	$0.00463
Haiku 4.5	$0.00020	$0.00231

Measured 10d ago against content hash 668a88bffece, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ha-bluetooth-augment 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 10d 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-bluetooth-augment/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HA Bluetooth Augment

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

Why this is a skill, not an agent

Human-visible augmentation surface — the user describes how the device advertises and reads back the manifest matcher, the callback registration, the coordinator family, and the conformance report; a skill keeps this on the visible command surface, like the sibling augment skills (ha-discovery-augment, ha-config-flow-augment, ha-coordinator-add).
Mid-flow interactivity — the passive-vs-connectable decision, the coordinator-family choice, and the network-discovery redirect are per-run dialogues the user approves before generation.
Bounded, inline generation — the manifest matcher plus the callback registration and the coordinator wiring fit inline; no isolated agent context is needed.
Counter-dimension considered: the draft→validate loop could be an agent, but the connectable decision and the trade-off advice belong in the user's working context; skill wins.

When this skill activates

Use this skill to add Bluetooth support — central BLE discovery plus advertisement-driven data fetching — to an existing integration, typically for a device that delivers its data over BLE advertisements (the passive default) or needs an occasional active connection.

When NOT to activate

DHCP/SSDP/USB/HomeKit/Zeroconf network or bus discovery → ha-discovery-augment / ha/discovery-mechanisms
the config-flow Bluetooth discovery step / generic config-flow auth steps → ha-config-flow-augment / ha/config-flow-patterns
the generic polling-based DataUpdateCoordinator for REST/cloud APIs → ha/coordinator-patterns
greenfield integration scaffolding → ha-integration-scaffold
deploying/importing into a running HA instance → out of scope

Hard rules

Read spec/ha/bluetooth/en.md first. Do not generate HA internals from memory.
Right mechanism, with delimitation. DHCP/SSDP/USB/HomeKit/Zeroconf → ha-discovery-augment; the full config-flow discovery step → ha-config-flow-augment. Redirect rather than augmenting the wrong one.
Manifest matcher + dependency. The bluetooth key is a list of matcher dicts from the documented fields (service_uuid, local_name, manufacturer_id, service_data_uuid, connectable); add bluetooth_adapters to dependencies when the integration uses an adapter.
Passive is the default. Operate connectable=False whenever the device delivers data through advertisements only — that opts in to non-connectable controllers. Use connectable=True (the field default) only where an outgoing connection is actually needed; set the flag per device for mixed devices.
Advertisement callbacks. Subscribe via bluetooth.async_register_callback(hass, callback, matcher, mode) with a BluetoothCallbackMatcher and an explicit bluetooth.BluetoothScanningMode (ACTIVE/PASSIVE). The callback is @callback, synchronous, signature (service_info: BluetoothServiceInfoBleak, change: BluetoothChange) -> None. Bind the returned cancel callback via entry.async_on_unload(...).
Lookups, never an own scanner. Get a BLEDevice via bluetooth.async_ble_device_from_address(hass, address, connectable) and handle the None case (no adapter in range); read latest info via bluetooth.async_last_service_info; check bluetooth.async_scanner_count(hass, connectable=True) at setup when connecting. Never instantiate an own BleakScanner.
Right coordinator family. PassiveBluetoothProcessorCoordinator for sensors/binary sensors/events from advertisements; ActiveBluetoothProcessorCoordinator on connection need; the DataUpdate variants for non-sensor entities; the generic DataUpdateCoordinator only on pure connection communication with no advertisements. Processor coordinators format PassiveBluetoothDataUpdate (indexed by PassiveBluetoothEntityKey) and bind coordinator.async_start() to entry.async_on_unload(...) only after async_forward_entry_setups. Active variants check CoreState.running and a reachable connectable BLEDevice in needs_poll_method.
Connection handling. For active connections use bluetooth.async_get_scanner(hass), a fresh BleakClient per connection, a timeout ≥ 10 s, and bleak-retry-connector; never hold a permanent connection when the data is in advertisements.
Name per spec/ha/naming-conventions/en.md and verify HA internals against the official docs (see spec/ha/upstream-docs-verification/en.md).

Read the full file on GitHub · 112 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.

10d ago First seen · 112 lines · 204 tokens per session scan A 668a88bffece

Subscribe to this mod's changes

ha-bluetooth-augment is a skill published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 204 tokens to every session and 2,314 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.

Claude Code Hardware and IoT agents anthropic automation blueprints bluetooth claude custom-integration home-assistant

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

c-bluetooth

Manage Bluetooth devices on macOS using the blucli (blu) CLI. List paired and available devices, connect to headphones/speakers/keyboards, and disconnect devices by name or MAC address.

daxaur/openpaw · 44 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