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-fleet-scaffoldgit 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-fleet-scaffold)<a href="https://agentmods.dev/skills/nolte/claude-home-assistant/ha-esphome-fleet-scaffold"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-esphome-fleet-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.
<a href="https://agentmods.dev/skills/nolte/claude-home-assistant/ha-esphome-fleet-scaffold"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-esphome-fleet-scaffold.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 | $0.00218 | $0.02361 |
| Opus 5 | $0.00109 | $0.01180 |
| Sonnet 5 | $0.00044 | $0.00472 |
| Haiku 4.5 | $0.00022 | $0.00236 |
Grade A, and why
ha-esphome-fleet-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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HA ESPHome Fleet Scaffold
Spec: spec/claude/ha-esphome-fleet-scaffold/en.md (EN canonical) / spec/claude/ha-esphome-fleet-scaffold/de.md (DE translation). Grounding spec: spec/ha/esphome-project-structure/en.md; the device-file half is spec/ha/esphome-config-patterns/en.md.
Establishes the repository structure an ESPHome fleet is built in — once, at the top — so every later device is one new file and every shared concern has exactly one home.
Why this is a skill, not an agent
- Mid-flow approval is the contract (decisive): the config root, the package cut, and — on an existing repository — which files move where are decisions the operator confirms before anything is written; a fire-and-forget agent would restructure a repository on guesses.
- Repository-shaping change in the current context: the operator iterates on the proposed tree ("keep
src/", "noimages/yet") in conversation, which is main-thread territory per the change-scope dimension. - Counter-dimension considered: the inventory pass over an existing repository is read-heavy and self-contained (agent bias) — but the read volume is bounded by the fleet's YAML files, and the migration decision must stay visible; skill wins. The read-only conformance verdict on an existing layout is the agent case, and it is owned by
ha-esphome-fleet-reviewer.
When this skill activates
The user is setting up or restructuring an ESPHome repository — "set up a repo for my ESPHome devices", "meine ESPHome-Configs aufräumen", "wo soll das gemeinsame Zeug hin" — as opposed to writing a single device.
When NOT to activate
- one device file, new or extended →
ha-esphome-config-scaffold/ha-esphome-config-augment - one package to cut, parameterise, or de-duplicate →
ha-esphome-package-author - the CI workflow that validates the fleet →
ha-esphome-ci-scaffold - a conformance verdict on an existing layout →
ha-esphome-fleet-reviewer(read-only) - portfolio-wide repository scaffolding that is not ESPHome-specific (Taskfile, pre-commit, Renovate, docs) → the inherited
project/specs and their skills - compiling, flashing, or fleet OTA rollout → the ESPHome toolchain / operator
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 · 102 lines · 218 tokens per session scan A dab0104388b2
ha-esphome-fleet-scaffold is a skill published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 218 tokens to every session and 2,361 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"…