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.
npx skills add daxaur/openpaw --skill c-voicegit clone --depth 1 https://github.com/daxaur/openpawWrote 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/daxaur/openpaw/c-voice)<a href="https://agentmods.dev/skills/daxaur/openpaw/c-voice"><img src="https://agentmods.dev/badge/skills/daxaur/openpaw/c-voice.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.00430 |
| Opus 5 | $0.00022 | $0.00215 |
| Sonnet 5 | $0.00009 | $0.00086 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
c-voice 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 7d 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.
What it actually says
What This Skill Does
Enables Claude to transcribe spoken audio to text via sag (powered by ElevenLabs) and to speak text aloud using the macOS say command.
Available CLI Tools
sag — Speech-to-Text (ElevenLabs)
# Transcribe an audio file
sag transcribe --file recording.mp3
# Record from microphone and transcribe
sag record --output transcript.txt
# Transcribe with a specific language hint
sag transcribe --file audio.wav --language en
# Output transcript to stdout
sag transcribe --file audio.m4a --stdout
say — Text-to-Speech (macOS built-in)
# Speak text aloud
say "Hello, how can I help you today?"
# Use a specific voice
say -v Samantha "Your report is ready."
# Save spoken audio to a file
say -o output.aiff "Text to synthesize"
# List available voices
say -v ?
# Control speaking rate (words per minute)
say -r 180 "Speaking at a custom rate"
Usage Guidelines
- Use
sagto process audio files the user provides or to capture mic input - Use
sayto read back responses, summaries, or alerts aloud - Prefer
say -v Samanthaor-v Alexfor natural-sounding output on macOS
Notes
sagrequires a valid ElevenLabs API key configured in environmentsayis built into macOS — no installation needed- Supported audio input formats for
sag: MP3, WAV, M4A, FLAC
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.
- 7d ago First seen · 59 lines · 44 tokens per session scan A 82c9fb9f6fd1
c-voice is a skill published in the GitHub repository daxaur/openpaw (167 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 430 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
talkback
Speak an explanation out loud while working in any project — tiered text-to-speech with a pluggable backend (ElevenLabs by default and quota-guarded, macOS say via --fast for free instant local speech, local OmniVoice as an unlimited private tier). Markdown-aware, so code fences, URLs and deep paths collapse to short…
voice
Plant Sprachaufnahme, Transkription und Sprachausgabe mit optionalen, austauschbaren Werkzeugen.
tts-synthesizer
Text-to-speech synthesis - read documents, multiple voices and engines.
sag
ElevenLabs text-to-speech with mac-style say UX.
videoagent-audio-studio
Tired of juggling multiple audio APIs? This skill gives you one-command access to TTS, music generation, sound effects, and voice cloning. Use when you want to generate any audio without managing multiple API keys.
multimodal-llm
Vision, audio, video generation, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, generating AI video (Kling v3, Sora 2, Veo 3.1 std/lite/fast, Runway Gen-4.5 via gen4turbo), or building multimodal AI pipelines.