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 L3DigitalNet/Claude-Code-Plugins --skill ha-diagnosticsgit 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-diagnostics)<a href="https://agentmods.dev/skills/l3digitalnet/claude-code-plugins/ha-diagnostics"><img src="https://agentmods.dev/badge/skills/l3digitalnet/claude-code-plugins/ha-diagnostics/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/l3digitalnet/claude-code-plugins/ha-diagnostics"><img src="https://agentmods.dev/badge/skills/l3digitalnet/claude-code-plugins/ha-diagnostics.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 | $0.00041 | $0.01834 |
| Opus 5.5 | $0.00016 | $0.00734 |
| Sonnet 5.5 | $0.00008 | $0.00367 |
| Haiku 4.5 | $0.00004 | $0.00183 |
Grade A, and why
ha-diagnostics 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 — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Home Assistant Diagnostics Implementation
Diagnostics provide users and developers with structured debug information while protecting sensitive data. Required for Gold tier on the Integration Quality Scale.
File Structure
custom_components/{domain}/
├── __init__.py
├── diagnostics.py # Diagnostics implementation
└── ...
Basic diagnostics.py Template
"""Diagnostics support for {Name}."""
from __future__ import annotations
from typing import Any
from homeassistant.components.diagnostics import async_redact_data
from homeassistant.config_entries import ConfigEntry
from homeassistant.core import HomeAssistant
# Keys to redact from diagnostics output
TO_REDACT = {
# Authentication
"password",
"token",
"api_key",
"access_token",
"refresh_token",
"secret",
"credentials",
# Personal information
"email",
"username",
"serial",
"serial_number",
"unique_id",
"mac",
"mac_address",
# Location
"latitude",
"longitude",
"location",
"address",
}
async def async_get_config_entry_diagnostics(
hass: HomeAssistant, entry: ConfigEntry
) -> dict[str, Any]:
"""Return diagnostics for a config entry."""
coordinator = entry.runtime_data
return {
"config_entry": async_redact_data(entry.as_dict(), TO_REDACT),
"coordinator_data": async_redact_data(
coordinator.data if coordinator.data else {}, TO_REDACT
),
}
Advanced Diagnostics with Device Info
"""Diagnostics support for {Name}."""
from __future__ import annotations
from typing import Any
from homeassistant.components.diagnostics import async_redact_data
from homeassistant.config_entries import ConfigEntry
from homeassistant.core import HomeAssistant
from homeassistant.helpers import device_registry as dr, entity_registry as er
TO_REDACT = {
"password",
"token",
"api_key",
"access_token",
"refresh_token",
"secret",
"email",
"username",
"serial",
"serial_number",
"unique_id",
"user_id",
"credentials",
"mac",
"mac_address",
"latitude",
"longitude",
}
# Additional keys in nested structures
TO_REDACT_NESTED = TO_REDACT | {"ip_address", "host", "ssid"}
async def async_get_config_entry_diagnostics(
hass: HomeAssistant, entry: ConfigEntry
) -> dict[str, Any]:
"""Return diagnostics for a config entry."""
coordinator = entry.runtime_data
# Get device and entity info
device_registry = dr.async_get(hass)
entity_registry = er.async_get(hass)
devices = []
for device in dr.async_entries_for_config_entry(device_registry, entry.entry_id):
entities = []
for entity in er.async_entries_for_device(
entity_registry, device.id, include_disabled_entities=True
):
entities.append({
"entity_id": entity.entity_id,
"disabled": entity.disabled,
"disabled_by": entity.disabled_by,
"platform": entity.platform,
})
devices.append({
"name": device.name,
"model": device.model,
"manufacturer": device.manufacturer,
"sw_version": device.sw_version,
"hw_version": device.hw_version,
"entities": entities,
})
return {
"config_entry": {
"entry_id": entry.entry_id,
"version": entry.version,
"domain": entry.domain,
"title": entry.title,
"data": async_redact_data(dict(entry.data), TO_REDACT),
"options": async_redact_data(dict(entry.options), TO_REDACT),
},
"devices": devices,
"coordinator": {
"last_update_success": coordinator.last_update_success,
"last_exception": str(coordinator.last_exception) if coordinator.last_exception else None,
"update_interval": str(coordinator.update_interval),
"data": async_redact_data(coordinator.data, TO_REDACT_NESTED) if coordinator.data else None,
},
}
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 · 302 lines · 41 tokens per session scan A 7a32b775a157
ha-diagnostics is a skill published in the GitHub repository L3DigitalNet/Claude-Code-Plugins (8 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,834 once invoked, about $0.0002 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
gke-ai-troubleshooting-tpu-dynamic-slices-monitoring
Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use…
gke-ai-troubleshooting-tpu-vbar-oom
Diagnoses and prevents vbarcontrolagent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbarcontrolagent crashes, memory cgroup OOMs in serial console…
doca-flow
DOCA Flow packet steering on NVIDIA NICs/DPUs, linked into a C application: match/action pipes, ports, representors, forwarding, hairpin, counters. Trigger on packet steering, classifier, rule-matching, representor, hairpin or 5-tuple-to-queue questions even when "DOCA Flow" is not named. Remote or non-C++ control…
competition-firmware-layout
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for firmware images, partition tables, boot chains, update packages, extracted filesystems, embedded configs, and device-facing trust boundaries. Use when the user asks to unpack firmware, map partition layout, inspect bootloader or init…
diagnose-driver-install
Diagnose NVIDIA driver installation failures on DeepOps-managed nodes — nvidia-smi errors, "No devices were found", DKMS build failures, or GPU pods crash-looping. Use before reinstalling anything.
catc-troubleshoot
Catalyst Center troubleshooting workflows - device unreachable investigation, client connectivity issues, interface down analysis, site-wide outage triage, wireless roaming problems, integration with pyATS for CLI-level diagnostics. Use when the device is managed by Catalyst Center and you want its…