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 larsboes/Axon --skill ha-dashboardgit clone --depth 1 https://github.com/larsboes/AxonWrote 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/larsboes/axon/ha-dashboard)<a href="https://agentmods.dev/skills/larsboes/axon/ha-dashboard"><img src="https://agentmods.dev/badge/skills/larsboes/axon/ha-dashboard/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/larsboes/axon/ha-dashboard"><img src="https://agentmods.dev/badge/skills/larsboes/axon/ha-dashboard.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 | $0.00167 | $0.01314 |
| Opus 5 | $0.00084 | $0.00657 |
| Sonnet 5 | $0.00033 | $0.00263 |
| Haiku 4.5 | $0.00017 | $0.00131 |
Grade A, and why
ha-dashboard scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ha-dashboard
Deploy and back up Home Assistant Lovelace dashboards over the WebSocket API. Lovelace
dashboard config lives behind HA's WebSocket API, not its REST API, so this is a
pure-Python-3 stdlib WebSocket client (socket + ssl + base64 + hashlib) — no
websockets package, no pip install. Commands: list, backup, deploy, create.
The non-secret HA_URL comes from the committed overlay config; the secret HA_TOKEN
comes from a Bitwarden item at runtime, never hardcoded.
Setup (once)
- In Home Assistant: create a long-lived access token (Profile → Security → Long-lived
access tokens). That token is
HA_TOKEN. - In the overlay config: set
HA_URL(e.g.http://<host>:8123, or anhttps://reverse-proxy URL) in<overlay>/config/home-assistant.vars(override the root with$AXON_HOME_ROOT). The WebSocket URL is derived from it. - In Bitwarden: an item
home-assistant/ha(override with$HA_BW_ITEM) holding only the secret fieldHA_TOKEN— the same item ha-cli uses. Provision via Axonsetup-secret.sh. - Point
bwat the vault once:bw config server <vault-url>.
Run
Unlock Bitwarden interactively, then call (the tool reads $BW_SESSION, never the master password):
export BW_SESSION=$(bw unlock --raw)
# Inspect
scripts/ha-dashboard list # every named dashboard + the default
scripts/ha-dashboard list -j # JSON
# Back up before overwriting (default dashboard, or a named one)
scripts/ha-dashboard backup # -> default_dashboard_<ts>.json
scripts/ha-dashboard backup --url-path <slug> # -> <slug>_dashboard_<ts>.json
scripts/ha-dashboard backup --url-path <slug> -o mydash.json
# Deploy a config file (JSON always; YAML only if PyYAML happens to be installed)
scripts/ha-dashboard deploy mydash.json --url-path <slug>
scripts/ha-dashboard deploy overview.json # omit --url-path = default dashboard
# Create a new sidebar dashboard, then deploy into it
scripts/ha-dashboard create <slug> --title "My Dashboard" --icon mdi:home
What ships with it
1 file 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.
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.
- 9d ago First seen · 86 lines · 167 tokens per session scan A 98dab0da2b9e
ha-dashboard is a skill published in the GitHub repository larsboes/Axon (1 stars, last pushed yesterday), licensed MIT. It adds 167 tokens to every session and 1,314 once invoked, about $0.0008 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
usecase-smart-home-brain
Coordinate smart-home actions across existing integrations with clear dry-run and safety confirmation.
ryu-local-model
Search, download, and serve a local GGUF model on a Ryu node via Core's models and engines REST surface. Covers catalog search and device-fit, installing a specific quantization, activating a model, and listing engines (the engine is derived from the model format). Use when a user wants to get a local model running on…
beryl-it-tech
🛠️ Device, system, and network diagnosis.
it-work-reviewer
🔍 Evidence audit for device repair claims.
gx3-existing-project-audit
Analyze an existing Mitsubishi GX Works3 .gx3 project with gx3-cli when the user asks what a ladder does, why a device turns on, or whether a project has risks.
eight-sleep
Unofficial Eight Sleep pod data for AI agents. Writes stay fail-closed. Prefer MCP tools if connected; otherwise the package CLI. Use when the user wants Eight Sleep data or actions through an agent.