Borrowing it
Nothing to install: this file belongs to b1rdmania/ghostclaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/b1rdmania/ghostclaw/main/.claude/skills/add-voice-reply/SKILL.mdgit clone --depth 1 https://github.com/b1rdmania/ghostclawWrote 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/b1rdmania/ghostclaw/add-voice-reply)<a href="https://agentmods.dev/skills/b1rdmania/ghostclaw/add-voice-reply"><img src="https://agentmods.dev/badge/skills/b1rdmania/ghostclaw/add-voice-reply.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 | $0.00022 | $0.00417 |
| Opus 5 | $0.00011 | $0.00209 |
| Sonnet 5 | $0.00004 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
add-voice-reply scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Add Voice Replies (ElevenLabs)
When someone sends a voice note, the bot replies with a voice note instead of text. Uses ElevenLabs TTS.
Setup
1. ElevenLabs API key
Ask the user to:
- Sign up at elevenlabs.io
- Go to Settings > API Keys
- Copy the API key
Add to .env:
ELEVENLABS_API_KEY=<key>
2. Pick a voice
Ask: "Which voice should the bot use? You can browse voices at elevenlabs.io/voice-library, or use a custom/cloned voice."
If they have a specific voice, get the voice ID from the ElevenLabs dashboard. If not, suggest they browse the library and pick one that fits.
Add to .env:
ELEVENLABS_VOICE_ID=<voice_id>
If they skip this, the default voice will be used.
3. Rebuild and restart
npm run build
launchctl kickstart -k gui/$(id -u)/com.ghostclaw # macOS
# systemctl --user restart ghostclaw # Linux
4. Test
Tell the user to send a voice note to the bot. It should reply with a voice note using the selected voice. Text messages still get text replies.
How it works
The bot detects when an incoming message is a voice note (tagged [Voice: ...] after transcription). When replying to a voice message, it converts the text response to audio via ElevenLabs TTS and sends it as a voice note. Text messages always get text replies.
Disabling
Remove ELEVENLABS_API_KEY from .env and restart. The bot will fall back to text replies for everything.
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 · 56 lines · 22 tokens per session scan A 550137c76f84
add-voice-reply is a skill published in the GitHub repository b1rdmania/ghostclaw (92 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 417 once invoked, about $0.0001 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
video-frames
Extract a single frame from a local video at the first frame, a timestamp, or a zero-based frame index using FFmpeg.
ideation
Generate project ideas through creative constraints. Use when the user says 'I want to build something', 'give me a project idea', 'I'm bored', 'what should I make', 'inspire me', or any variant of 'I have tools but no direction'. Works for code, art, hardware, writing, tools, and anything that can be made.
clip-hand-skill
Expert knowledge for AI video clipping — yt-dlp downloading, whisper transcription, SRT generation, and ffmpeg processing.
xhs_note
A workflow for creating a Xiaohongshu post, a Chinese image-first social-media note, with short copy, hashtags, and at least three matching vertical images.
ai-drama-prompt-factory
A prompt-planning workflow that turns a novel or story idea into structured prompts for characters, locations, props, storyboard images, video, and audio. It produces prompt data for other AI generation tools rather than creating the media itself.
ad-ready
Generate advertising images automatically from a product URL + brand profile. ✅ USE WHEN: User provides a product URL (e-commerce link) Want automated product scraping + image generation Have a brand profile to apply (70+ brands available) Need funnel-stage targeting (awareness/consideration/conversion) Want AI to…