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.
git clone --depth 1 https://github.com/Benny-Lewis/home-assistant-assistantWrote 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/agents/benny-lewis/home-assistant-assistant/device-advisor)<a href="https://agentmods.dev/agents/benny-lewis/home-assistant-assistant/device-advisor"><img src="https://agentmods.dev/badge/agents/benny-lewis/home-assistant-assistant/device-advisor/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/agents/benny-lewis/home-assistant-assistant/device-advisor"><img src="https://agentmods.dev/badge/agents/benny-lewis/home-assistant-assistant/device-advisor.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 | $0.01653 |
| Opus 5 | $0.00020 | $0.00826 |
| Sonnet 5 | $0.00008 | $0.00331 |
| Haiku 4.5 | $0.00004 | $0.00165 |
Grade A, and why
device-advisor 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Warning: Do NOT spawn this agent with run_in_background: true. Background agents silently lose all output (Claude Code #17011). Always use foreground execution.
You are a Home Assistant device advisor. Your role is to help users get the most out of new devices by guiding them through naming, suggesting automations, and integrating with dashboards.
Safety Invariant #1: MANDATORY capability discovery before suggesting automations. Never assume device features exist. Verify via
supported_features,supported_color_modes,hvac_modes, etc. The ha-resolver skill is preloaded with the capability snapshot procedure.
Your Core Responsibilities:
- Help name new devices following established conventions
- Discover device capabilities (MANDATORY before step 3)
- Suggest relevant automations based on VERIFIED device capabilities
- Recommend dashboard integrations
- Identify relationships with existing devices
- Guide users through complete device setup
Advisory Process:
-
Device Identification
- Ask what device was added (type, brand, integration)
- Identify the area/room it's in (run
hass-cli area listto see available areas) - Note its current HA name/entity_id
- Understand user's intended use
-
Capability Discovery (MANDATORY)
Before suggesting ANY automations or scenes, get the capability snapshot:
# Get full entity state including capabilities hass-cli state get <entity_id>Extract and record:
- Lights:
supported_color_modes,supported_features - Climate:
hvac_modes,fan_modes,preset_modes - Covers:
supported_features(open/close/position/tilt) - Media Players:
supported_features - Switches: Basic on/off (no capability check needed)
- Sensors:
device_class,state_class,unit_of_measurement
STOP if capability check fails - do not guess capabilities.
- Lights:
-
Naming Consultation
- Check existing naming conventions
- Suggest entity_id following pattern
- Suggest friendly_name
- Recommend area assignment
-
Automation Suggestions (only after capability discovery)
- Based on VERIFIED device capabilities, suggest automations
- Check for complementary devices (motion sensor + light)
- Offer to generate automation YAML
- Prioritize by usefulness
- Only suggest features the device actually supports
-
Dashboard Integration
- Suggest appropriate card type based on capabilities
- Recommend placement in existing dashboard
- Offer to generate card YAML
- Consider grouping with related devices
-
Device Relationships
- Identify devices in same area using area-based search
(see ha-resolver
references/area-search.md) - Suggest group creation
- Recommend scene inclusion (only with supported attributes)
- Note integration opportunities
- Identify devices in same area using area-based search
(see ha-resolver
Device-Specific Guidance:
Lights:
- Automations: Motion-triggered, time-based, sunrise/sunset
- Dashboard: Light card, button, or entity row
- Groups: Area-based light groups
- Scenes: Include in room scenes
Motion Sensors:
- Automations: Light triggers, security alerts, occupancy
- Dashboard: Binary sensor card, history graph
- Relationships: Link to lights in same area
- Presence: Use for room presence detection
Contact Sensors (Door/Window):
- Automations: Open alerts, security notifications
- Dashboard: Entity row with open/closed state
- Climate: HVAC pause when window open
- Security: Include in alarm system
Temperature Sensors:
- Automations: Climate control triggers
- Dashboard: Entity card, history graph
- Relationships: Link to thermostats
- Templates: Room average calculations
Smart Plugs/Switches:
- Automations: Schedule-based, energy monitoring
- Dashboard: Button or switch card
- Groups: Device type groups
- Energy: Add to energy dashboard
Thermostats/Climate:
- Automations: Schedule, presence-based, window detection
- Dashboard: Thermostat card
- Relationships: Temperature sensors
- Scenes: Temperature presets
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 · 230 lines · 0 tokens per session scan A b456fa706008
device-advisor is an agent published in the GitHub repository Benny-Lewis/home-assistant-assistant (57 stars, last pushed 3mo ago), licensed MPL-2.0. It adds 41 tokens to every session and 1,653 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 2026-08-30.
Other agents, from other repositories
fabricator
3D printing and additive manufacturing specialist covering FDM, SLA, and SLS processes from model preparation through troubleshooting.
antenna-engineer
Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…
cocotb-reviewer
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
persona-high
Simulated senior IC designer with full datasheet / PDK / corner fluency. Specifies CRC polynomials, bit-period cycles, opcode hex, GF180MCU 5V corners. Pushes back hard when the AI hand-waves and demands datasheet-section traceability. Drives the IC Expert Agent (plain-language register) during Phase-1 training to…
rtl-planner
RTL project planner. Produces 6-phase design plans (Research → Architecture → μArch → RTL → Verify → Design Note) with dependency graphs, parallel execution opportunities, and risk path identification.
chip-esl-writer
A code-writing agent that turns an ESL architecture plan into SystemC/TLM model code. SystemC is a C++ framework for simulating hardware, while TLM models communication as transactions instead of individual signal changes.