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 magnusoverli/opencode --skill home-assistant-troubleshootinggit clone --depth 1 https://github.com/magnusoverli/opencodeWrote 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/magnusoverli/opencode/home-assistant-troubleshooting)<a href="https://agentmods.dev/skills/magnusoverli/opencode/home-assistant-troubleshooting"><img src="https://agentmods.dev/badge/skills/magnusoverli/opencode/home-assistant-troubleshooting.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 5.1 | $0.00089 | $0.01083 |
| Opus 5 | $0.00044 | $0.00541 |
| Sonnet 5 | $0.00018 | $0.00217 |
| Haiku 4.5 | $0.00009 | $0.00108 |
Grade A, and why
home-assistant-troubleshooting 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 7d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Troubleshooting Home Assistant
This work is read-only and ends in a recommendation. Gather evidence, explain what it shows, propose the smallest fix — and stop. Do not edit files, call services, restart, reload, or "just try" a change while investigating. The user asks for a fix separately, and then the configuration skill applies.
Keep queries bounded
Diagnostics is where context gets burned. Every query below has a narrower form; use it. A dump of every entity or a full log crowds out the evidence that actually matters.
get_home_contextbefore any broad listing — it answers most "what exists" questions in a fraction of the tokens.search_entitieswith a pattern, notget_stateswith no filter.get_states(domain=...)when you do need a list.get_history/get_logbookover the shortest window that could show the problem. Start at a few hours, widen only if it is not there. Supplied timestamps must carryZor a UTC offset.get_error_logbeforeget_support_logs; the error log is already filtered.get_support_logswhen you need Core, Supervisor, host or add-on logs — it is bounded and credential-redacted. Name the component and keep the line count small.
If a query comes back empty, that means that query found nothing. Widen the window or change the search term before concluding the thing does not exist.
Order of attack
Start with diagnose_entity whenever the report names an entity. It bundles
current state, recent history, related entities and the common causes, so it
usually replaces four separate calls.
Then, depending on what it shows:
| Symptom | Next evidence |
|---|---|
unavailable / unknown |
get_entity_details for the integration and device; get_devices for the parent device; the integration's entries in get_error_log |
| Entity missing entirely | search_entities for the old and new names; check whether it was renamed or the integration failed to load |
| Automation did not fire | get_logbook for the automation entity; read the automation YAML; check each condition against get_history at the trigger time |
| Template error | render_template with the exact expression; check the referenced entities exist and are not unknown |
| Value looks wrong | get_history for the entity, then for its source entity |
| Integration failing to set up | get_error_log; get_supervisor_resolution for known issues |
| Slow, restarting, or out of space | get_supervisor_health, get_supervisor_metrics, get_backup_posture, get_store_audit |
| Something changed after an update | get_breaking_changes; the release notes for the installed version |
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.
- 7d ago First seen · 88 lines · 89 tokens per session scan A e3d84a0858f3
home-assistant-troubleshooting is a skill published in the GitHub repository magnusoverli/opencode (375 stars, last pushed 5d ago), licensed Unlicense. It adds 89 tokens to every session and 1,083 once invoked, about $0.0004 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 2026-08-30.
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…
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…
doca-flow
Build and debug DOCA Flow applications on supported NVIDIA NICs/DPUs: define match/action pipes, initialize ports and representors, choose forwarding targets, validate pipes before hardware programming, read counters, match the Flow version to the installed DOCA release, and diagnose Flow API errors. Trigger on DOCA…
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 a device is unreachable, a user reports connectivity problems, an interface…