Borrowing it
Nothing to install: this file belongs to PowerBeef/Vocello. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/PowerBeef/Vocello/main/.claude/skills/vocello-device-diagnostics/SKILL.mdgit clone --depth 1 https://github.com/PowerBeef/VocelloWrote 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/powerbeef/vocello/vocello-device-diagnostics)<a href="https://agentmods.dev/skills/powerbeef/vocello/vocello-device-diagnostics"><img src="https://agentmods.dev/badge/skills/powerbeef/vocello/vocello-device-diagnostics/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/powerbeef/vocello/vocello-device-diagnostics"><img src="https://agentmods.dev/badge/skills/powerbeef/vocello/vocello-device-diagnostics.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 | $0.00025 | $0.00258 |
| Opus 5.5 | $0.00010 | $0.00103 |
| Sonnet 5.5 | $0.00005 | $0.00052 |
| Haiku 4.5 | $0.00003 | $0.00026 |
Grade A, and why
vocello-device-diagnostics 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
Physical-device diagnostics
Arguments: $ARGUMENTS
Read docs/reference/ios-device-testing.md and docs/reference/native-engineering.md. Use
scripts/ios_device.sh help to select its current verb; begin with doctor or device-state when
the environment is uncertain. Prefer retained logs/crashes first. Run only the relevant
scripts/ios_device.sh <verb> <options>; this driver is headless, not a native UI driver.
Use a quiet committed checkpoint for measured bench/lang-bench/memory/profile lanes, after joining
workers. No new models/downloads, distribution-candidate install/launch or external publication
without specific authorization. Candidate acceptance uses the documented preinstalled-candidate route.
Print only privacy-safe summaries; retain raw artifacts untracked. Classify the result and crash
delta accurately. Never retry silently or replace failed evidence. MobileBuildMCP runs only its
discovery and coverage workflows (its device and debugging workflows stay off); repository scripts own
the final evidence.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed 5d051df2f74e
- 16d ago Changed · +4 lines b025bd6296d9
- 18d ago First seen · 18 lines · 25 tokens per session scan A 0910a97db2da
vocello-device-diagnostics is a skill published in the GitHub repository PowerBeef/Vocello (386 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 258 once invoked, about $0.0001 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 2026-10-11.
Other skills, from other repositories
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…
localvoxtral-doctor
Use when the user's localvoxtral dictation misbehaves, for example a dictation did not join this session, its text was not inserted, or speech or polish failed. Names the localvoxtral commands that check the setup and read the app's log.
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.
voice-settings
Choose Cadence Code's local speech and transcription models from the Codex or Antigravity UI. Use only when the user explicitly invokes $voice-settings, /voice-settings, or asks to open Cadence Code settings.
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…