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.
npx skills add nolte/claude-home-assistant --skill ha-device-registry-augmentgit 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/skills/nolte/claude-home-assistant/ha-device-registry-augment)<a href="https://agentmods.dev/skills/nolte/claude-home-assistant/ha-device-registry-augment"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-device-registry-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.
<a href="https://agentmods.dev/skills/nolte/claude-home-assistant/ha-device-registry-augment"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-device-registry-augment.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 | $0.00211 | $0.01952 |
| Opus 5 | $0.00105 | $0.00976 |
| Sonnet 5 | $0.00042 | $0.00390 |
| Haiku 4.5 | $0.00021 | $0.00195 |
Grade A, and why
ha-device-registry-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 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HA Device Registry Augment
Spec: spec/claude/ha-device-registry-augment/en.md (EN canonical) / spec/claude/ha-device-registry-augment/de.md (DE translation).
This skill owns the device-registry hierarchy — DeviceInfo, via_device, dynamic device add, and stale device removal — that ha/entity-architecture describes but no skill wires. It lifts an integration from flat entities toward the Gold devices / stale-devices / dynamic-devices rules.
Why this is a skill, not an agent
- Human-visible augmentation surface — the user describes the device topology and reads back the
DeviceInfowiring, thevia_devicelink, and the removal path; a skill keeps this on the visible command surface, like the sibling augment skills. - Mid-flow interactivity — the device topology (one device, a hub with children, per-datapoint devices), the identifier source, and whether stale-device removal applies are per-run dialogues the user confirms.
- Bounded, inline generation — the
DeviceInfoconstruction plus the removal hook fits inline; no isolated agent context is needed. - Counter-dimension considered: the draft→validate loop could be an agent, but the topology decision and the report belong in the user's working context; skill wins.
When this skill activates
Use this skill when an existing integration's entities should group into one or more devices — a single device, a hub with via_device children, or per-physical-device grouping — and when devices that disappear from the backend must be removed from the registry.
When NOT to activate
- creating the entity platform itself →
ha-entity-platform-add/ha-entity-description-map - config-entry diagnostics (the JSON dump) →
ha-diagnostics-augment - device trigger / condition / action automation platforms →
ha-device-automation-add - greenfield integration setup →
ha-integration-scaffold - deploying/importing into a running HA instance → out of scope (generation only)
Hard rules
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.
- 11d ago First seen · 103 lines · 211 tokens per session scan A a0edd7a169d1
ha-device-registry-augment is a skill published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 211 tokens to every session and 1,952 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.
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.
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.
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.
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.
stride-analysis-patterns
Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.
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"…