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 yandex-speaker-bringupgit 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/yandex-speaker-bringup)<a href="https://agentmods.dev/skills/howdeploy/deploychan_mcp/yandex-speaker-bringup"><img src="https://agentmods.dev/badge/skills/howdeploy/deploychan_mcp/yandex-speaker-bringup/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/yandex-speaker-bringup"><img src="https://agentmods.dev/badge/skills/howdeploy/deploychan_mcp/yandex-speaker-bringup.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 | $0.00059 | $0.00712 |
| Opus 5.5 | $0.00024 | $0.00285 |
| Sonnet 5.5 | $0.00012 | $0.00142 |
| Haiku 4.5 | $0.00006 | $0.00071 |
Grade A, and why
Bring up an owned Yandex speaker for an agent 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 today.
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.
What it actually says
Speaker bring-up
Use the exact user-owned target and requested features. The reference experience is Mini 1 YNDX-0004; other models require their own compatibility evidence. This skill is a procedure, not a bundled exploit/firmware installer.
- Identify hardware label, current build, power/data connection, host OS, router
control and existing access. State which functions require the PC or a provider.
If connected to Deploychan MCP, retrieve
yandex-speaker-feasibilityfor the matrix. - Read the current community root instructions and matching device page. Preserve network settings and explain any required reset. Do not update or reset an unidentified device just to see whether access appears.
- Prepare the chosen local/scoped bootstrap and verify it is ready before directing the user to change DNS or connect the speaker. Record each original setting and corresponding undo step. Confirm real requests/access, not only service status.
- Inspect and apply the appropriate SSH/update procedure within authorization. Protect maintenance access from untrusted networks and record actual persistence. Do not copy immutable markers or scripts across models.
- Acquire private, versioned backup evidence. Preserve identity/geometry, tools,
hashes and incomplete reads. Distinguish corrected logical NAND, raw/OOB dumps,
USB ADB and hardware recovery. Do not write bootloader or factory identity as
a routine bring-up step. Details:
yandex-speaker-access-and-recoveryvia MCP. - Restore original household DNS and retire bootstrap services at a safe boundary. Keep device isolation and LAN maintenance separate. Inspect boot restoration, IPv6 and vendor error behavior instead of assuming a firewall creates a local assistant.
- Verify an agreed reboot/recovery boundary only when authorized. Record actual access, service restoration and retained volume/settings; leave unperformed recovery tests explicitly unverified.
Use community recovery for model-specific rollback. A replacement assistant daemon, BetterYAM and USB-host/AirPlay recipes are optional migrations/features; do not install them just because root is available.
Deliver a short feasibility/access report, private backup location, changes and rollback, user actions still required, and the next audio/agent integration step. Never publish the backup, device identity, account data, LAN addressing or credentials.
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.
- today First seen · 57 lines · 59 tokens per session scan A 73ad5f0aaa7c
Bring up an owned Yandex speaker for an agent is a skill published in the GitHub repository howdeploy/deploychan_mcp (19 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 712 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
amazon-alexa
Integracao completa com Amazon Alexa para criar skills de voz inteligentes, transformar Alexa em assistente com Claude como cerebro (projeto Auri) e integrar com AWS ecosystem (Lambda, DynamoDB, Polly, Transcribe, Lex, Smart Home).
hardware-health-check
Out-of-band hardware health via Redfish BMC (read-only) — power state, component health, thermal and power readings, firmware inventory, SEL log triage. Use when determining whether a host is powered off versus unreachable, checking hardware faults, reviewing thermal or PSU state, or triaging BMC event logs.
hz-psdk-integration
Guides interactive Horizon Platform SDK (PSDK) integration for Meta VR and Horizon OS Android/Kotlin apps — analyzes the codebase, recommends public platform features, plans the integration, and validates on device. Use for workflow guidance; use hz-platform-sdk for the detailed API reference. Build paths: Standard…
hz-unity-meta-movement-sdk-retargeting
Set up and tweak Meta Movement SDK (MSDK) retargeting for a character model. Use this whenever the user wants to retarget a humanoid FBX/prefab for Meta VR body tracking, generate a retargeting config, or hand-edit the resulting .json (fix known-joint mappings, exclude joints from auto-mapping, rename target joints…
hz-quest-verify-first
MANDATORY pre-flight check before answering any question or writing any code related to Meta Quest VR headsets (Quest 2, Quest 3, Quest 3S, Quest Pro) or apps that target them. Forces verification against authoritative Meta sources via the metavr CLI / metavr MCP tools BEFORE relying on training-data knowledge.…
hz-unity-face-tracking
Drive ARKit-blendshape-rigged head/face models in Unity with the wearer's facial expressions on Meta VR via Meta Movement SDK (face tracking + A2E). Use when a user has an FBX with the 52 ARKit blendshapes (any prefix, L/R suffixes) and wants it to animate from face tracking on Quest Pro / Quest 3 / Quest 3S.