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 T0mSIlver/localvoxtral --skill localvoxtral-doctorgit clone --depth 1 https://github.com/T0mSIlver/localvoxtralWrote 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/t0msilver/localvoxtral/localvoxtral-doctor)<a href="https://agentmods.dev/skills/t0msilver/localvoxtral/localvoxtral-doctor"><img src="https://agentmods.dev/badge/skills/t0msilver/localvoxtral/localvoxtral-doctor/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/t0msilver/localvoxtral/localvoxtral-doctor"><img src="https://agentmods.dev/badge/skills/t0msilver/localvoxtral/localvoxtral-doctor.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 | $0.00410 |
| Opus 5.5 | $0.00024 | $0.00164 |
| Sonnet 5.5 | $0.00012 | $0.00082 |
| Haiku 4.5 | $0.00006 | $0.00041 |
Grade A, and why
localvoxtral-doctor 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 19d 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.
What it actually says
localvoxtral diagnostics
localvoxtral is the speech-to-text app the user dictates with, on their Mac.
A dictation "joins" a coding agent session when the app finds the session it
was spoken into and uses that session's context. Two commands report on it.
Both take --json and change nothing.
localvoxtral doctor checks the app and where the localvoxtral command
points, the microphone and Accessibility permissions, the speech and polish
engines, each coding agent's plugin or hooks and dictation note, each remote
host, and which session the last five dictations joined. Each check reads ok,
warning, failed or skipped, and each problem names the step that fixes it.
Exit status: 0 nothing failed, 3 the app is not running, 4 a check failed.
On a remote host, localvoxtral doctor first checks this host's end of the
tunnel to the Mac: the forwarded port, whether the Mac's listener accepts the
token, the installed Claude Code plugin against the version each running
session loaded, the Vibe hooks and the last hook's outcome. It then prints
the Mac's checks for this host.
localvoxtral logs prints the app's lines from the Mac's unified log: one
line per dictation saying which session it joined and why, and the app's
errors. --join keeps only the join lines, and --since widens the window
from the last hour (12h, 3d, 2026-09-25). It works while the app is not
running, and only on the Mac.
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.
- 19d ago First seen · 31 lines · 59 tokens per session scan A d36e28e3eed9
localvoxtral-doctor is a skill published in the GitHub repository T0mSIlver/localvoxtral (59 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 410 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 2026-10-03.
Other skills, from other repositories
reproducible-github-issues
Use this skill when the user wants to create, improve, or triage a reproducible GitHub issue for MLX-VLM, including bug reports from CLI inference, server inference, model loading, processors, media inputs, dependency setup, crashes, wrong outputs, or performance regressions.
benchmark
Run performance + quality benchmarks. ASR reports WER, RTF, process memory, and throughput across engines/variants. Arguments include asr, tts, vad, diarize, asr-quick.
review-pr
Review a pull request for conceptual fit, architecture impact, adversarial failure modes, security risk, docs impact, regression risk, test coverage, and merge readiness. Use when asked to review a PR, check whether a PR is safe to merge, decide if more tests are needed, perform adversarial or security review, or…
vocello-design
Historical Vocello 2.0 prototype reference only; not a current production skill or acceptance source.
start-talking
Start and run an explicit, interactive Cadence Code conversation with Codex or Antigravity using fully local speech input and output. Use only when the user explicitly invokes $start-talking, /start-talking, or asks to start talking with Cadence Code.
vox-voice-alerts
Speak a short spoken alert to the user via the vox text-to-speech CLI whenever you hand the turn back to them — a task finished (pass or fail, however long it took), you're blocked and need input/a decision/approval, something broke, or you're about to go quiet on a long job. Assume the user is NOT watching the…