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 JosephScript/claude-speaknpx agentmods add plugins/josephscript/claude-speak/marketplacegit clone --depth 1 https://github.com/JosephScript/claude-speakGrade A, and why
claude-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-speak",
"id": "claude-speak",
"owner": {
"name": "JosephScript",
"email": "[email protected]"
},
"metadata": {
"description": "Give Claude a voice on macOS or Linux — on-demand and automatic speech output, adjustable rate/voice/truncation.",
"version": "1.0.0"
},
"plugins": [
{
"name": "claude-speak",
"source": "./",
"description": "Give Claude a voice on macOS (`say`) or Linux (`espeak-ng`) — on-demand /speak (verbatim or LLM-summarized), an automatic toggle-speak Stop hook, and adjustable rate/voice/truncation.",
"version": "1.1.0",
"author": {
"name": "JosephScript",
"email": "[email protected]"
},
"keywords": ["voice", "tts", "accessibility", "macos", "linux", "espeak", "say"],
"category": "productivity",
"homepage": "https://github.com/JosephScript/claude-speak"
}
]
}
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 · 28 lines scan A ad9da9ec9703
claude-speak is a plugin published in the GitHub repository JosephScript/claude-speak (3 stars, last pushed 29d 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
claude-code-audio-recap
Plugin marketplace listing 1 plugin: audio-recap.
audio-recap
Audio Recap for Claude Code — listen to each assistant turn: a one-sentence recap of what Claude did, then the message itself, with long replies summarized for ears.
gnome-ui-plugins
Bundled plugins for GNOME desktop automation through MCP.
gnome-ui-mcp
GNOME Wayland desktop automation via AT-SPI discovery and Mutter input.
macwright-skills
Project-specific skills for the MacWright MCP server — Safari automation, screen coordinate system, tool development patterns, and workflows discovered during iterative testing.
server-control
Control any computer remotely from Claude — Linux, macOS, or Windows. Run commands, manage services, edit files, and monitor your system via SSH.