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 agentmods add skills/nodnarbnitram/claude-code-extensions/ha-integrationnpx skills add nodnarbnitram/claude-code-extensions --skill ha-integrationgit clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensionsWhat 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 | $0.00063 | $0.03908 |
| Opus 5 | $0.00032 | $0.01954 |
| Sonnet 5 | $0.00013 | $0.00782 |
| Haiku 4.5 | $0.00006 | $0.00391 |
Grade A, and why
ha-integration scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
data = requests.get("https://api.example.com/data").json() How it starts
The opening of the file, as written. The whole thing — 559 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Home Assistant Integration Development
Create professional-grade custom Home Assistant integrations with complete config flows and entity implementations.
⚠️ BEFORE YOU START
This skill prevents 8 common integration errors and saves ~40% implementation time.
| Metric | Without Skill | With Skill |
|---|---|---|
| Setup Time | 45 minutes | 12 minutes |
| Common Errors | 8 | 0 |
| Config Flow Issues | 5+ | 0 |
| Entity Registration Bugs | 4+ | 0 |
Known Issues This Skill Prevents
- Missing manifest.json dependencies - Forgetting to declare required Home Assistant components
- Async/await issues - Not properly awaiting coordinator updates and entity initialization
- Entity state class mismatches - Using wrong STATE_CLASS (measurement vs total) for sensor platforms
- Config flow schema errors - Invalid vol.Schema definitions causing validation failures
- Device info not linked - Entities created without proper device registry connections
- Coordinator errors - Not handling data update failures gracefully
- Platform import timing - Loading platform files before component initialization
- Missing unique ID generation - Creating duplicate entities across restarts
Quick Start
Step 1: Create manifest.json
{
"domain": "my_integration",
"name": "My Integration",
"codeowners": ["@username"],
"config_flow": true,
"documentation": "https://github.com/username/ha-my-integration",
"requirements": [],
"version": "0.0.1"
}
Why this matters: The manifest.json defines integration metadata, declares dependencies, and enables config flow UI in Home Assistant.
Step 2: Create init.py with async setup
import asyncio
from homeassistant.config_entries import ConfigEntry
from homeassistant.core import HomeAssistant
from homeassistant.exceptions import ConfigEntryNotReady
from .coordinator import MyDataUpdateCoordinator
DOMAIN = "my_integration"
async def async_setup_entry(hass: HomeAssistant, entry: ConfigEntry) -> bool:
"""Set up the integration from config entry."""
hass.data.setdefault(DOMAIN, {})
# Create coordinator
coordinator = MyDataUpdateCoordinator(hass, entry)
await coordinator.async_config_entry_first_refresh()
hass.data[DOMAIN][entry.entry_id] = coordinator
# Forward setup to platforms
await hass.config_entries.async_forward_entry_setups(entry, ["sensor"])
return True
async def async_unload_entry(hass: HomeAssistant, entry: ConfigEntry) -> bool:
"""Unload the integration."""
unload_ok = await hass.config_entries.async_unload_platforms(entry, ["sensor"])
if unload_ok:
hass.data[DOMAIN].pop(entry.entry_id)
return unload_ok
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/__init__.py 1.5 KB runs code
- assets/config_flow.py 3.9 KB runs code
- assets/const.py 75 B runs code
- assets/coordinator.py 2.0 KB runs code
- assets/manifest.json 340 B
- assets/sensor.py 3.6 KB runs code
- README.md 6.1 KB
- references/config-flow-patterns.md 7.4 KB
- references/entity-base-classes.md 6.5 KB
- references/manifest-reference.md 3.8 KB
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.
- 2d ago First seen · 559 lines · 63 tokens per session scan A 08eb1296f8a6
ha-integration is a skill published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 63 tokens to every session and 3,908 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…