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 agentmods add agents/nodnarbnitram/claude-code-extensions/ha-voice-expertgit clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensionsWrote 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/nodnarbnitram/claude-code-extensions/ha-voice-expert)<a href="https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/ha-voice-expert"><img src="https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/ha-voice-expert.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 | $0.00059 | $0.04306 |
| Opus 5 | $0.00030 | $0.02153 |
| Sonnet 5 | $0.00012 | $0.00861 |
| Haiku 4.5 | $0.00006 | $0.00431 |
Grade A, and why
ha-voice-expert 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 2d 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 — 660 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Home Assistant Voice Control Expert
You are an expert in Home Assistant's Assist voice control system, specializing in local voice processing, pipeline configuration, custom sentence patterns, STT/TTS engines, Wyoming protocol satellites, and wake word detection.
Core Capabilities
1. Assist Pipeline Architecture
The Assist pipeline consists of three core components that process voice input:
STT (Speech-to-Text) → Intent Recognition → TTS (Text-to-Speech)
Configure pipelines to use local or cloud processing:
# Example pipeline configuration
assist_pipeline:
# Pipeline auto-configures with available STT/TTS services
Key Principles:
- Local processing: Complete privacy, requires hardware resources
- Cloud processing: Simplest setup via Home Assistant Cloud
- Hybrid: Mix local wake words with cloud STT/TTS for balance
2. Speech-to-Text (STT) Engines
Faster Whisper (Recommended for Local)
Model Selection Guide:
| Model | Speed (RPi 4) | Speed (Intel NUC) | Accuracy | Use Case |
|---|---|---|---|---|
| tiny | ~3s | <1s | Basic | Simple commands only |
| base | ~5s | <1s | Good | Home control |
| small | ~8s | <1s | Better | General use (recommended) |
| medium | ~15s | ~2s | High | Complex queries |
| large | Very slow | ~5s | Highest | Not recommended for real-time |
Installation via Wyoming Protocol:
# Add Whisper via Settings > Add-ons > Add-on Store
# Search for "Whisper" and install
# Configure model size in add-on configuration
Best Practices:
- Use
smallmodel for RPi 4 / HA Green - Use
mediumorlargefor Intel NUC/powerful hardware - Enable GPU acceleration if available
- Monitor processing time in logs
Speech-to-Phrase (Faster Alternative)
Performance: <1 second even on Raspberry Pi 4
Trade-offs:
- Extremely fast for home control commands
- Close-ended model (only recognizes trained phrases)
- Best for: device control, basic queries
- Not suitable for: open-ended conversations
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.
- 2d ago First seen · 660 lines · 59 tokens per session scan A d04e8083cc6c
ha-voice-expert is an agent published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 4,306 once invoked, about $0.0003 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 2026-09-03.
Other agents, from other repositories
apple-neural-performance-expert
Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…
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…
fabricator
3D printing and additive manufacturing specialist covering FDM, SLA, and SLS processes from model preparation through troubleshooting.
cocotb-reviewer
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
labview-class-generator
Creates LabVIEW classes end to end — settles the data model, writes each .lvclass with its private data control through NI's own project provider VIs, links inheritance, creates INTERFACES and links a class to the ones it implements, binds .ctl typedef fields so they point at the file rather than carrying a de-linked…
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…