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 jason-c-dev/claude-code-speaknpx agentmods add plugins/jason-c-dev/claude-code-speak/marketplacegit clone --depth 1 https://github.com/jason-c-dev/claude-code-speakGrade A, and why
claude-code-speak 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": "claude-code-speak",
"owner": {
"name": "Jason",
"email": "[email protected]"
},
"metadata": {
"description": "Claude Code plugin that speaks Claude's responses aloud via Deepgram, Piper, or macOS `say`",
"version": "0.2.0"
},
"plugins": [
{
"name": "claude-speech",
"source": "./",
"description": "Speaks the natural-language portions of Claude's responses aloud. Three TTS backends (Deepgram Aura-2 cloud, Piper local neural, macOS `say` local classic) with automatic fallback. Three modes: end-of-turn, with pre-tool cues, or hybrid with attention alerts.",
"version": "0.2.0",
"author": {
"name": "Jason"
},
"category": "developer-experience",
"keywords": [
"speech",
"tts",
"deepgram",
"piper",
"aura",
"accessibility",
"macos"
]
}
]
}
What ships with it
1 file beside marketplace.json 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.
- yesterday First seen · 33 lines scan A f4d8b93514b8
claude-code-speak is a plugin published in the GitHub repository jason-c-dev/claude-code-speak (2 stars, last pushed 4mo ago), 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
mcp-voice-soundboard-local
Local marketplace for the MCP Voice Soundboard plugin.
mcp-voice-soundboard
Text-to-speech for Claude Code. 48 voices, 9 languages, emotion spans, SSML-lite, multi-speaker dialogue, SFX tags, and built-in guardrails.
mojiemoji-github
GitHub Markdown 向け mojiemoji 画像スタンプを埋め込むスキル + サブエージェント + 6 必須パラメータゲートフック.
yaps
Plugin marketplace listing 12 plugins: yaps-memory, yaps-dictation, yaps-transcription, yaps-meeting-transcription, yaps-srt-generator.
yaps-audio-cleaner
Remove background noise, hiss, and static from speech recordings locally with Yaps.
yaps-meeting-transcription
Transcribe meetings, interviews, podcasts, and calls with accurate speaker labels using Yaps.