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-blueprint-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-blueprint-scaffold)<a href="https://agentmods.dev/skills/nolte/claude-home-assistant/ha-blueprint-scaffold"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-blueprint-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-blueprint-scaffold"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-blueprint-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 | $0.00180 | $0.01753 |
| Opus 5 | $0.00090 | $0.00877 |
| Sonnet 5 | $0.00036 | $0.00351 |
| Haiku 4.5 | $0.00018 | $0.00175 |
Grade A, and why
ha-blueprint-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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HA Blueprint Scaffold
Spec: spec/claude/ha-blueprint-scaffold/en.md (EN canonical) / spec/claude/ha-blueprint-scaffold/de.md (DE translation).
This skill is the entry point for creating a blueprint. It does not generate the YAML itself — it gathers parameters, runs a pre-flight, and dispatches the ha-blueprint-author agent, which owns the draft → validate → iterate loop and the conformance report against spec/ha/blueprint-patterns/en.md.
Why this is a skill, not an agent
- Orchestrator role (decisive): the procedure gathers intent interactively, runs the pre-flight, and then dispatches the
ha-blueprint-authoragent for the heavy authoring — perskill-vs-agent, the orchestrator in the hybrid pattern is always a skill. - Mid-flow interactivity: blueprint intent (domain, inputs, trigger shape) is elicited from the operator before any file exists; that dialogue lives in the main conversation.
- Counter-dimension considered: the YAML authoring itself is self-contained (agent bias) — which is exactly why it is delegated to the sibling agent instead of making this wrapper an agent.
When this skill activates
Use this skill when the user wants to create one Home Assistant blueprint (automation, script, or template) from a described intent — typically to package a reusable automation for sharing or for their own home.
When NOT to activate
- scaffolding a Python custom integration →
ha-integration-scaffold - scaffolding a Lovelace card →
ha-lovelace-card-scaffold - defining an integration service →
ha-service-definition-add - importing, deploying, or pushing a blueprint into a running HA instance → out of scope (generation only)
Hard rules
- Never generate the blueprint inline. The
ha-blueprint-authoragent is the sole generation path; this skill gathers inputs, pre-flights, dispatches, and relays. Do not rebuild the agent's loop here. - Intent is mandatory. Without a described intent there is no dispatch. Everything else may fall back to a documented default.
- Never overwrite an existing blueprint. If the resolved path already exists, abort with the path quoted. Collision is a user-disambiguation problem.
- Never silently default. When the user is silent on
domain,target_dir,author, orsource_url, use the documented defaults — but state every default in the dispatch and in the relayed report. - One blueprint, one domain, one run. No multi-blueprint batches, no Python, no live-HA import.
- Verify HA internals against the official docs. Don't reproduce HA API signatures, lifecycle hooks, conventions, or schemas from memory — when uncertain, consult the official docs before generating or relying on it: Developer docs
developers.home-assistant, architecture/blueprint/YAML docshome-assistant.io(seespec/ha/upstream-docs-verification/en.md).
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 · 98 lines · 180 tokens per session scan A 790c8cc8425a
ha-blueprint-scaffold is a skill published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 180 tokens to every session and 1,753 once invoked, about $0.0009 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"…