Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/paulpreibisch/AgentVibesnpx agentmods add commands/paulpreibisch/agentvibes/audio-browserWrote 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/commands/paulpreibisch/agentvibes/audio-browser)<a href="https://agentmods.dev/commands/paulpreibisch/agentvibes/audio-browser"><img src="https://agentmods.dev/badge/commands/paulpreibisch/agentvibes/audio-browser/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/commands/paulpreibisch/agentvibes/audio-browser"><img src="https://agentmods.dev/badge/commands/paulpreibisch/agentvibes/audio-browser.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 | $0.00033 | $0.00689 |
| Opus 5.5 | $0.00013 | $0.00276 |
| Sonnet 5.5 | $0.00007 | $0.00138 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
audio-browser 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 1mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Launch the AgentVibes Voice Browser. After the user selects a voice, you (the agent) will automatically switch AgentVibes to that voice.
Step 1 — Open the Voice Browser
node bin/agentvibes-voice-browser.js
Wait for the user to browse, preview voices (Space), and install one (I). The browser will save the selection to ~/.agentvibes/config.json.
Step 2 — After the Browser Closes, Read the Selected Voice
cat ~/.agentvibes/config.json 2>/dev/null || echo "{}"
Look at the defaultVoice field and ttsProvider field in the output.
Step 3 — Switch AgentVibes to the Selected Voice
Based on what was installed, run the appropriate command:
Piper curated voice (e.g., en_US-amy-medium, ryan, bryce):
bash .claude/hooks/voice-manager.sh switch <defaultVoice>
LibriTTS multi-speaker voice (e.g., libritts-speaker-42):
- Extract the speaker ID from the voice name (the number after
libritts-speaker-) - Download the model if needed:
bash .claude/hooks/piper-voice-manager.sh download en_US-libritts-high
- Register the speaker in
.claude/hooks/piper-multispeaker-registry.shby adding an entry toMULTISPEAKER_VOICES:
"Speaker_<ID>:en_US-libritts-high:<ID>:LibriTTS Speaker"
- Switch to it:
bash .claude/hooks/voice-manager.sh switch Speaker_<ID>
macOS voice (provider = macos):
bash .claude/hooks/voice-manager.sh switch <defaultVoice>
(Ensure piper provider is not active — switch provider to macos first if needed)
Windows SAPI voice (provider = windows-sapi):
bash .claude/hooks/voice-manager.sh switch <defaultVoice>
Key Bindings in the Browser
| Key | Action |
|---|---|
Space |
Preview voice |
I |
Install voice as AgentVibes default |
P |
Show copy-paste prompt for this voice |
L |
Filter by provider |
F |
Show favorites only |
/ |
Search voices |
1-6 |
Sort by column |
T |
Switch to Background Music tab |
Q |
Quit |
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.
- 1mo ago First seen · 78 lines · 33 tokens per session scan A 1fd47f799e1f
audio-browser is a command published in the GitHub repository paulpreibisch/AgentVibes (156 stars, last pushed 2d ago), licensed Apache-2.0. It adds 33 tokens to every session and 689 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 2026-09-03.
Other commands, from other repositories
domains
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
delivery-profiles
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
audit-code
When /audit-code [target] is invoked, immediately execute the following steps to analyze code quality, security, and adherence to project standards.
plan-delegate
Execution: work a roadmap as supervisor, brief an implementation agent per item, verify its work independently, then record and commit it.
sparc-post-deployment-monitoring-mode
📈 Deployment Monitor - You observe the system post-launch, collecting performance, logs, and user feedback. You flag reg...
setup
Command "setup" from jazz-max/ruflo-hub, covering setting up ruv-swarm hooks, quick start, 1. initialize with hooks, 2. test hook functionality and test pre-edit hook.