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/l3digitalnet/claude-code-plugins/ha-device-triggersnpx skills add L3DigitalNet/Claude-Code-Plugins --skill ha-device-triggersgit clone --depth 1 https://github.com/L3DigitalNet/Claude-Code-PluginsWrote 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/l3digitalnet/claude-code-plugins/ha-device-triggers)<a href="https://agentmods.dev/skills/l3digitalnet/claude-code-plugins/ha-device-triggers"><img src="https://agentmods.dev/badge/skills/l3digitalnet/claude-code-plugins/ha-device-triggers.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.01333 |
| Opus 5 | $0.00017 | $0.00666 |
| Sonnet 5 | $0.00007 | $0.00267 |
| Haiku 4.5 | $0.00003 | $0.00133 |
Grade A, and why
ha-device-triggers 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 4d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Home Assistant Device Triggers
Device triggers allow automations to be triggered by device-specific events, like button presses or motion detection.
Note: Device triggers/conditions/actions are optional UX features, not Integration Quality Scale (IQS) rules — unlike diagnostics and repairs, they are not among the 52 IQS rules. Don't implement them to advance an IQS tier; only add them when the device genuinely benefits from device-based automation.
When to Use Device Triggers
Use device triggers when:
- Device has physical buttons or inputs
- Device generates events (motion, doorbell press)
- Hardware state changes need automation triggers
- Standard entity triggers aren't sufficient
File Structure
custom_components/{domain}/
├── device_trigger.py # Trigger implementation
├── device_condition.py # See ha-device-conditions-actions
├── device_action.py # See ha-device-conditions-actions
└── strings.json # Trigger labels
device_trigger.py Template
"""Device triggers for {Name}."""
from __future__ import annotations
from typing import Any
import voluptuous as vol
from homeassistant.components.device_automation import DEVICE_TRIGGER_BASE_SCHEMA
from homeassistant.components.homeassistant.triggers import event as event_trigger
from homeassistant.const import CONF_DEVICE_ID, CONF_DOMAIN, CONF_PLATFORM, CONF_TYPE
from homeassistant.core import CALLBACK_TYPE, HomeAssistant
from homeassistant.helpers import device_registry as dr
from homeassistant.helpers.trigger import TriggerActionType, TriggerInfo
from homeassistant.helpers.typing import ConfigType
from .const import DOMAIN
# Define trigger types your device supports
TRIGGER_TYPES = {"button_press", "button_long_press", "motion_detected"}
TRIGGER_SCHEMA = DEVICE_TRIGGER_BASE_SCHEMA.extend(
{
vol.Required(CONF_TYPE): vol.In(TRIGGER_TYPES),
}
)
async def async_get_triggers(
hass: HomeAssistant, device_id: str
) -> list[dict[str, Any]]:
"""Return a list of triggers for this device."""
device_registry = dr.async_get(hass)
device = device_registry.async_get(device_id)
if device is None:
return []
# Check if this device belongs to our integration
if DOMAIN not in [id[0] for id in device.identifiers]:
return []
triggers = []
# Add triggers based on device capabilities
# In a real integration, check device.model or stored capabilities
for trigger_type in TRIGGER_TYPES:
triggers.append(
{
CONF_PLATFORM: "device",
CONF_DEVICE_ID: device_id,
CONF_DOMAIN: DOMAIN,
CONF_TYPE: trigger_type,
}
)
return triggers
async def async_attach_trigger(
hass: HomeAssistant,
config: ConfigType,
action: TriggerActionType,
trigger_info: TriggerInfo,
) -> CALLBACK_TYPE:
"""Attach a trigger."""
event_config = event_trigger.TRIGGER_SCHEMA(
{
event_trigger.CONF_PLATFORM: "event",
event_trigger.CONF_EVENT_TYPE: f"{DOMAIN}_event",
event_trigger.CONF_EVENT_DATA: {
CONF_DEVICE_ID: config[CONF_DEVICE_ID],
CONF_TYPE: config[CONF_TYPE],
},
}
)
return await event_trigger.async_attach_trigger(
hass, event_config, action, trigger_info, platform_type="device"
)
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.
- 4d ago First seen · 197 lines · 34 tokens per session scan A d1522e2390de
ha-device-triggers is a skill published in the GitHub repository L3DigitalNet/Claude-Code-Plugins (6 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 1,333 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…