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.
/plugin marketplace add punt-labs/voxnpx agentmods add plugins/punt-labs/vox/plugingit clone --depth 1 https://github.com/punt-labs/voxGrade A, and why
vox-dev 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.
What it actually says
{
"name": "vox-dev",
"description": "Text-to-speech for Claude Code: /unmute, /mute, /vibe, /vox:recap",
"version": "5.0.3",
"author": {
"name": "Punt Labs",
"email": "[email protected]"
},
"mcpServers": {
"mic": {
"type": "stdio",
"command": "vox",
"args": [
"mcp"
]
}
}
}
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 · 19 lines scan A 300215585705
vox-dev is a plugin published in the GitHub repository punt-labs/vox (3 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.
Other plugins, from other repositories
langlearn-tts-dev
Suppress MCP tool output for langlearn-tts in Claude Code.
video-recap
Turn any video into a Chinese-narration recap on ffmpeg + one Xiaomi MiMo API key.
video-recap-skills
Turn any video into a Chinese-narration recap on ffmpeg + one Xiaomi MiMo API key: understanding (ASR + VLM) -> narration -> cut -> voiceover -> assemble. A bundle of independent skills + a thin orchestrator. Runs on macOS, Linux, and Windows.
quarry-dev
Local semantic search for Claude Code: /find, /ingest, /remember, /explain, /source, /quarry.
beadle-dev
Autonomous agent daemon with cryptographic owner control. Email communication via IMAP/SMTP with PGP trust model.
biff-dev
UNIX-style team communication for Claude Code: /who, /finger, /plan, /write, /read, /mesg, /tty, /last, /wall, /talk.