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 howdeploy/deploychan_mcp --skill local-voice-command-traininggit clone --depth 1 https://github.com/howdeploy/deploychan_mcpWrote 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/howdeploy/deploychan_mcp/local-voice-command-training)<a href="https://agentmods.dev/skills/howdeploy/deploychan_mcp/local-voice-command-training"><img src="https://agentmods.dev/badge/skills/howdeploy/deploychan_mcp/local-voice-command-training/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/howdeploy/deploychan_mcp/local-voice-command-training"><img src="https://agentmods.dev/badge/skills/howdeploy/deploychan_mcp/local-voice-command-training.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 | $0.00050 | $0.00861 |
| Opus 5.5 | $0.00020 | $0.00344 |
| Sonnet 5.5 | $0.00010 | $0.00172 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
Train and integrate local wake words and short commands 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 yesterday.
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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local wake and command work
Use the user's chosen word, device and interaction contract. For the rationale and
case matrix retrieve local-wake-word-and-command-training from Deploychan MCP;
upstream microWakeWord covers wake-model
training, while any multi-command head/router extension must be implemented separately.
For KISA's actual Mini 1 stack also retrieve yandex-mini1-reference-stack before
choosing the runtime or capture method. It specifies the side-by-side ARM TFLite
Micro runner, Quasar :9850 vqe_0 subscription, supervisor lifecycle and artifact
inventory. Do not assume a downloadable runner is included, propose a Kaldi .nnet
as a compatible substitute, or remove native audio services to free ALSA for this path.
Diagnose before requesting another recording
Read frontend shape/rate, label order, actual model path, native runtime, supervisor and crop/endpoint logic. Determine whether inference is on the speaker or host. Trace one failed phrase from audio through candidate scores to execution/dictation. Check wake consumption, pre-roll, body-window boundaries, confidence/margin, pause gate and a stale deployment before attributing every miss to the training samples.
Use a shared frontend/network when it suits a small vocabulary. Do not present that custom adaptation as generic ASR or promise capacity for an arbitrary number of commands. Desktop actions can use host ASR and a deterministic parser without expanding this model.
Collect and evaluate
- Establish capture readiness; then tell the user to speak. Preserve a session ID, label, intended phrase, source recording and train/validation assignment.
- During collection disable effects and outgoing agent dictation. Collect normal, fast, quiet and distant variants, short/long aliases, confusable negatives and ordinary sentences mentioning the action words. Keep recordings private.
- Retain independent recordings outside training. Record when tuning against a validation set turns it into a regression set; do not claim independent accuracy.
- Evaluate both one-breath and wake/pause/body forms, repeated wake, bare commands, command mentions and silence. Compare the same WAV on host and target runtime. State any simulated VAD/ASR events. Respect the user's limits on test execution.
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.
- yesterday First seen · 74 lines · 50 tokens per session scan A 0f66c90415f2
Train and integrate local wake words and short commands is a skill published in the GitHub repository howdeploy/deploychan_mcp (19 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 861 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-28.
Other skills, from other repositories
huawei-cloud-cloudrobo-model-workflow
Model development orchestration Skill covering asset query, model training, inference deployment, and real-robot evaluation in any combination. Supports full end-to-end pipeline or partial stages (e.g., train+deploy only, deploy+eval only). When user requirements involve two or more stages, prefer this Skill over…
automotive-commands
192 automation scripts for 33 command categories: testing, diagnostics, ADAS, AUTOSAR, safety, etc.
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
holoscan-install-wheel
Install Holoscan SDK 5.x CUDA 13 Python wheels in an isolated environment, choosing the full stack or version-matched components.
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…