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 agentmods add commands/enesbasbug/voice-to-claude/configgit clone --depth 1 https://github.com/enesbasbug/voice-to-claudeWrote 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/commands/enesbasbug/voice-to-claude/config)<a href="https://agentmods.dev/commands/enesbasbug/voice-to-claude/config"><img src="https://agentmods.dev/badge/commands/enesbasbug/voice-to-claude/config.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 | $0.00015 | $0.01637 |
| Opus 5 | $0.00008 | $0.00818 |
| Sonnet 5 | $0.00003 | $0.00327 |
| Haiku 4.5 | $0.00002 | $0.00164 |
Grade A, and why
config scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
voice-to-claude Configuration
Change voice-to-claude settings including the Whisper model, hotkey, and output mode.
Instructions
When the user runs /voice-to-claude:config:
Step 1: Show current configuration
PYTHON_CMD=$([ -f "${CLAUDE_PLUGIN_ROOT}/.venv/bin/python" ] && echo "${CLAUDE_PLUGIN_ROOT}/.venv/bin/python" || (command -v python3.11 >/dev/null && echo python3.11) || (command -v python3.10 >/dev/null && echo python3.10) || echo python3); $PYTHON_CMD ${CLAUDE_PLUGIN_ROOT}/scripts/exec.py config show
Display current settings:
Current Configuration
========================================
Model: base
Hotkey: Ctrl+Alt
Output: keyboard
Sounds: enabled
Language: auto-detect
Task: transcribe
Step 2: Ask what to change
Ask the user what they'd like to configure:
- Model - Change Whisper model (affects quality/speed)
- Hotkey - Change the recording hotkey
- Output - Change how text is inserted (keyboard/clipboard)
- Sounds - Enable/disable audio feedback
- Language - Force a specific language (ISO 639-1, e.g.
es) orauto - Task -
transcribe(keep source language) ortranslate(to English)
Changing Model
Available models:
| Model | Size | Speed | Quality |
|---|---|---|---|
| tiny | ~75MB | ~0.5s | Basic |
| base | ~142MB | ~1s | Good (default) |
| medium | ~1.5GB | ~2s | Better |
| large-v3 | ~3GB | ~3s | Best |
To change model, first check if it's downloaded:
PYTHON_CMD=$([ -f "${CLAUDE_PLUGIN_ROOT}/.venv/bin/python" ] && echo "${CLAUDE_PLUGIN_ROOT}/.venv/bin/python" || (command -v python3.11 >/dev/null && echo python3.11) || (command -v python3.10 >/dev/null && echo python3.10) || echo python3); $PYTHON_CMD ${CLAUDE_PLUGIN_ROOT}/scripts/exec.py config model <model_name>
If model isn't downloaded, download it:
cd ~/.local/share/voice-to-claude/whisper.cpp && ./models/download-ggml-model.sh <model_name>
Then set it:
PYTHON_CMD=$([ -f "${CLAUDE_PLUGIN_ROOT}/.venv/bin/python" ] && echo "${CLAUDE_PLUGIN_ROOT}/.venv/bin/python" || (command -v python3.11 >/dev/null && echo python3.11) || (command -v python3.10 >/dev/null && echo python3.10) || echo python3); $PYTHON_CMD ${CLAUDE_PLUGIN_ROOT}/scripts/exec.py config model <model_name>
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.
- 5d ago First seen · 136 lines · 15 tokens per session scan A a6c1203c4e30
config is a command published in the GitHub repository enesbasbug/voice-to-claude (10 stars, last pushed 8d ago), licensed MIT. It adds 15 tokens to every session and 1,637 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 2026-08-31.
Other commands, from other repositories
on
Enable Audio Recap for this Claude Code session.
recent
Show recent voice transcripts and corrections.
wheel-to-talk-stop
Stop the Wheel to Talk backend.
wheel-to-talk-setup
Enable voice dictation and start the Wheel to Talk backend.
squirrel-custom
View or edit custom segments — your own text, a command's output, or a recurring reminder.
squirrel-rules
View or surgically edit the bar rules — paint the whole status line when a condition holds (usage high, repo dirty, session idle, …).