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-dev-workflow-applygit 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-dev-workflow-apply)<a href="https://agentmods.dev/skills/nolte/claude-home-assistant/ha-dev-workflow-apply"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-dev-workflow-apply/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-dev-workflow-apply"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-dev-workflow-apply.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 | $0.00212 | $0.02557 |
| Opus 5.5 | $0.00085 | $0.01023 |
| Sonnet 5.5 | $0.00042 | $0.00511 |
| Haiku 4.5 | $0.00021 | $0.00256 |
Grade A, and why
ha-dev-workflow-apply 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 1mo 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HA Dev-Workflow Apply
Spec: spec/claude/ha-dev-workflow-apply/en.md (EN canonical) / spec/claude/ha-dev-workflow-apply/de.md (DE translation). Grounding spec: spec/ha/dev-workflow/en.md — this skill operationalises that spec's MUST rules; read it for the pinned HA-original rules.
This skill is the owning skill of spec/ha/dev-workflow: it applies the HA coding workflow (style, strict typing, validation) to an existing Custom Integration and validates the result, closing the spec-vs-skill gap where the Platinum tier of ha-integration-solution previously resolved to a bare checklist item.
Why this is a skill, not an agent
- Human-visible apply surface — like the sibling
ha-translation-sync, the user invokes it directly, watches the format/typing/validation edits land, and reads the CONFORMANT / NEEDS-WORK report; a skill keeps that on the visible command surface. - Bounded, tool-driven work — it runs
ruff,mypy, andhassfestover one integration and applies mechanical fixes; the read/edit volume fits inline, so the pressure that biases toward an isolated agent does not apply. - Dispatched by an orchestrator —
ha-integration-solutiondispatches it fortarget_tier: platinum; the skill-orchestrates-skill default keeps it in skill form. - Counter-dimension considered: the strict-typing pass could run as a fire-and-forget agent, but the annotation edits and the mypy-strict decisions should stay visible and reviewable in the user context; skill wins.
When this skill activates
Use this skill to bring an existing Custom Integration under custom_components/<domain>/ up to the spec/ha/dev-workflow obligations — code style, full typing, hassfest, config validation — for a chosen target_tier (bronze floor through platinum). It is the tooling counterpart of the read-only ha-quality-scale-audit: that one checks the tier, this one applies the code-workflow rules that a tier requires.
When NOT to activate
- a read-only quality-scale tier assessment →
ha-quality-scale-audit - a security hardening audit →
ha-security-audit - the pytest harness (fixtures,
MockConfigEntry, snapshot tests, coverage) →ha-test-harness-augment/ha/test-harness - devcontainer / Kind /
script/setup/ venv bootstrap →ha/dev-environment - async / event-loop patterns →
ha/async-patterns - deploying / verifying against a running HA instance → the
ha-integration-deployer/ha-integration-verifieragents
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.
- 1mo ago First seen · 126 lines · 212 tokens per session scan A 99591c4f7203
ha-dev-workflow-apply is a skill published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 212 tokens to every session and 2,557 once invoked, about $0.0008 per session on Opus 5.5. 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
python-anti-patterns
Use this skill when reviewing Python code for common anti-patterns to avoid. Use as a checklist when reviewing code, before finalizing implementations, or when debugging issues that might stem from known bad practices.
python-code-style
Python code style, linting, formatting, naming conventions, and documentation standards. Use when writing new code, reviewing style, configuring linters, writing docstrings, or establishing project standards.
agent-django-fastapi-expert
Specialist subagent: Django ORM, Django REST Framework, FastAPI async patterns, and Pydantic v2 specialist. Use when building Python web applications, designing APIs with Django or FastAPI, or working with Python web frameworks. Trigger phrases: Django, FastAPI, DRF, Django REST Framework, Pydantic, ORM, queryset…
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
agent-python-expert
Specialist subagent: Python best practices, type hints, async patterns, and ecosystem expertise. Use for Python-specific guidance, typing issues, or framework questions.
ci-tests
Run the test suite for the current repo, auto-detecting Python (pytest/uv), Node (vitest/pnpm), or Rust (cargo test).