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.
git clone --depth 1 https://github.com/kellerza/hass-addonsWrote 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/rules/kellerza/hass-addons/python-tooling)<a href="https://agentmods.dev/rules/kellerza/hass-addons/python-tooling"><img src="https://agentmods.dev/badge/rules/kellerza/hass-addons/python-tooling/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/rules/kellerza/hass-addons/python-tooling"><img src="https://agentmods.dev/badge/rules/kellerza/hass-addons/python-tooling.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 | $0.00000 | $0.00435 |
| Opus 5.5 | $0.00000 | $0.00174 |
| Sonnet 5.5 | $0.00000 | $0.00087 |
| Haiku 4.5 | $0.00000 | $0.00044 |
Grade A, and why
python-tooling 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 12d 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.
What it actually says
Python conventions (src/)
- Python 3.13 only (
requires-python = ">=3.13,<3.14"). Use 3.13 syntax freely; no backport shims. - uv manages the env and runs code/tests. Run modules with
uv run -m <package>(e.g.uv run -m ha_addon_control_group) and tests withuv run pytest. Don't add deps by hand-editinguv.lock; add topyproject.tomland let uv resolve. - Layout:
pythonpath = src. Packages areha_addon,ha_addon_control_group,ha_addon_esp,ha_addon_qsusb64(seetool.uv.build-backend.module-name). Shared HA REST/ websocket helpers live insrc/ha_addon/ha_api/— reuse them, don't re-implement an HA client. - Lint/format: ruff with a broad select (
A,ASYNC,B,D,E,F,G,I,PGH,PIE,PL,PTH,PYI,RUF,UP,W). Notable:D(docstrings) is on,PTHmeans preferpathliboveros.path, line-ending islf.max-args = 7. Runuv run ruff checkanduv run ruff formatbefore finishing. - Async: code is async-first (
aiohttp,anyio); pytest runs withasyncio_mode = auto, soasync def test_*needs no marker. - Tests live in
src/tests/<addon>/and run with coverage. Per the ponytail rule, non-trivial logic gets one small test here.
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.
- 12d ago First seen · 26 lines · 0 tokens per session scan A b6631c1afc13
python-tooling is a cursor rule published in the GitHub repository kellerza/hass-addons (9 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 435 tokens. 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 2026-10-02.
Other cursor rules, from other repositories
ros
Definitive guidelines for writing high-quality, performant, and maintainable ROS 2 code, leveraging modern C++ and Python best practices, ament tooling, and efficient architectural patterns like node composition and multithreaded executors.
linux-nvidia-cuda-python-cursorrules-prompt-file
description: "Cursor rules for Linux development with NVIDIA CUDA and Python integration." globs: / alwaysApply: false.
code-style
Python code style, practices, lint/format rules, and common snippets.
testing
Testing rules — pytest, HA test harness, GitManager fixtures.
python_tests
We use the unit tests to cover internal behavior that can work without the web / backend counterpart. We aim for 95%+ unit test coverage of our Python code in lib/streamlit.
python-llm-ml-workflow-cursorrules-prompt-file
Cursor rules for Python LLM & ML development with workflow integration.