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-esphome-config-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-esphome-config-augment)<a href="https://agentmods.dev/skills/nolte/claude-home-assistant/ha-esphome-config-augment"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-esphome-config-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-esphome-config-augment"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-esphome-config-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 | $0.00209 | $0.01593 |
| Opus 5 | $0.00105 | $0.00796 |
| Sonnet 5 | $0.00042 | $0.00319 |
| Haiku 4.5 | $0.00021 | $0.00159 |
Grade A, and why
ha-esphome-config-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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HA ESPHome Config Augment
Spec: spec/claude/ha-esphome-config-augment/en.md (EN canonical) / spec/claude/ha-esphome-config-augment/de.md (DE translation). Grounding spec: spec/ha/esphome-config-patterns/en.md.
Adds exactly one addition to one existing device file per invocation, conforming to every MUST in the grounding spec.
Why this is a skill, not an agent
- Quick, targeted change in the current context (decisive): one block in one YAML file the conversation is already working on; per the change-scope and latency dimensions this routes to the main thread.
- Mid-flow approval: the component choice, target bus, and naming are confirmed with the operator before writing — a wrong bus binding on a multiplexed topology is expensive to debug on-device.
- Counter-dimension considered: schema lookup against the ESPHome docs is self-contained (agent bias), but the diff is small and iterated in conversation — isolation would cost more than it protects.
When this skill activates
The user asks to extend an existing ESPHome device — "add an SCD30 to box-02", "füge einen Sensor zum ESPHome-Gerät hinzu" — and the named device file exists.
When NOT to activate
- a brand-new device →
ha-esphome-config-scaffold - the shared package itself (cut, parameters,
!extend/!remove) →ha-esphome-package-author - a value or command Home Assistant drives →
ha-esphome-binding-add - authoring the custom component itself (C++/Python) → out of scope; no owning skill yet
- HA-side reactions to the new entities (automations, cards) →
ha-automation-solution/ha-lovelace-solution - compiling, flashing, or deploying → the ESPHome toolchain / operator
Hard rules
- Read
spec/ha/esphome-config-patterns/en.mdand the target device file (plus its shared packages/snippets) first. Do not generate from memory, and never add a block a shared package already provides. - Verify the component's schema against the official ESPHome docs (https://esphome.io) per
spec/ha/upstream-docs-verificationbefore writing; deprecated keys are findings, not output. - Naming stays substitution-derived (
${friendly_name}_<platform>_<n>_<measurement>);update_intervalprefers the device's existing interval substitution. - Credentials stay environment variables. A new block needing a credential reads it via
!env_varand the run reports the variable; never a literal, and never!secret— the grounding spec's credential mechanism is!env_var, which also works in packages where!secretprovably cannot. - Explicit bus binding. On multiplexed I2C topologies, bind the new block to a named
bus_id— never the implicit default bus. - One addition per run; one device file per run. Legacy
<<: !includemerge keys in the file are left as-is (never extended, never newly introduced). - No deploy. The skill ends at the edited file plus the validation step report.
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 · 93 lines · 209 tokens per session scan A 87993b13da5e
ha-esphome-config-augment is a skill published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 209 tokens to every session and 1,593 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.
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"…