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/ha-entity-resolver)<a href="https://agentmods.dev/agents/benny-lewis/home-assistant-assistant/ha-entity-resolver"><img src="https://agentmods.dev/badge/agents/benny-lewis/home-assistant-assistant/ha-entity-resolver/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/ha-entity-resolver"><img src="https://agentmods.dev/badge/agents/benny-lewis/home-assistant-assistant/ha-entity-resolver.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 | $0.00032 | $0.01310 |
| Opus 5 | $0.00016 | $0.00655 |
| Sonnet 5 | $0.00006 | $0.00262 |
| Haiku 4.5 | $0.00003 | $0.00131 |
Grade B, and why
ha-entity-resolver scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
PLUGIN_ROOT="$(cat .claude/ha-plugin-root.txt 2>/dev/null)" How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Entity Resolver Agent
Warning: Do NOT spawn this agent with run_in_background: true. Background agents silently lose all output (Claude Code #17011). Always use foreground execution.
Find Home Assistant entities matching user descriptions, validate they exist, and capture capability snapshots.
Safety Invariant #1: Always capture capability snapshots before suggesting attributes. Never assume features exist - verify via
supported_featuresor mode lists.
hass-cli: Use
hass-cli -o json state get <entity_id>for full attribute output (includessupported_features,supported_color_modes, etc.). Default tabular output only shows entity, description, state, and changed columns — not enough for capability snapshots.
Task
Given a description (e.g., "hallway motion sensor", "kitchen lights"), find the actual entity IDs and capture their capabilities.
Process
0. System orientation (optional — for unfamiliar setups)
If you don't know what areas or domains exist, run a quick overview first:
hass-cli state list | awk '$1 ~ /\./ {split($1, a, "."); print a[1]}' | sort | uniq -c | sort -rn
hass-cli area list
See ha-resolver references/system-overview.md for the full procedure.
1. Search for matching entities
Choose search strategy based on the query:
A. Query names a room/area (e.g., "kitchen lights", "bedroom sensors"): Use the area-search helper — it handles registry cross-referencing automatically.
First, resolve the helper path and Python command:
PLUGIN_ROOT="$(cat .claude/ha-plugin-root.txt 2>/dev/null)"
PY="$(cat .claude/ha-python.txt 2>/dev/null || command -v python3 || command -v python || command -v py)"
Then run the search:
$PY "$PLUGIN_ROOT/helpers/area-search.py" search "<area_name>"
# With domain filter:
$PY "$PLUGIN_ROOT/helpers/area-search.py" search "<area_name>" --domain light
# List all areas:
$PY "$PLUGIN_ROOT/helpers/area-search.py" list-areas
If the helper is unavailable (e.g. $PLUGIN_ROOT is empty), fall back to
hass-cli -o json entity list + hass-cli -o json area list — see
ha-resolver references/area-search.md.
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 · 159 lines · 32 tokens per session scan B 24067281c170
ha-entity-resolver 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 32 tokens to every session and 1,310 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.