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/startgit 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/start)<a href="https://agentmods.dev/commands/enesbasbug/voice-to-claude/start"><img src="https://agentmods.dev/badge/commands/enesbasbug/voice-to-claude/start.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 | $0.00006 | $0.00712 |
| Opus 5 | $0.00003 | $0.00356 |
| Sonnet 5 | $0.00001 | $0.00142 |
| Haiku 4.5 | $0.00001 | $0.00071 |
Grade A, and why
start scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start voice-to-claude Daemon
Start the speech-to-text daemon for voice dictation.
Instructions
When the user runs /voice-to-claude:start:
Step 1: Check if setup is complete
PYTHON_CMD=$([ -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); test -f ~/.config/voice-to-claude/config.json && $PYTHON_CMD -c "import json; c=json.load(open('$HOME/.config/voice-to-claude/config.json')); exit(0 if c.get('setup_complete') else 1)" 2>/dev/null && echo "SETUP_OK" || echo "SETUP_NEEDED"
- If output is
SETUP_NEEDED: Tell user to run/voice-to-claude:setupfirst. - If output is
SETUP_OK: Proceed to Step 2.
Step 2: Check daemon status
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 ${CLAUDE_PLUGIN_ROOT}/scripts/exec.py daemon status
Step 3: Start if not running
If daemon is not running:
PYTHON_CMD=$([ -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 ${CLAUDE_PLUGIN_ROOT}/scripts/exec.py daemon start --background
Step 4: Confirm and show usage
PYTHON_CMD=$([ -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 daemon status
Show usage reminder:
voice-to-claude daemon started.
Usage:
Hotkey: Ctrl+Alt (hold to record, release to transcribe)
1. Hold Ctrl+Alt - Recording starts
2. Speak clearly
3. Release - Text appears in input
Tips:
- Speak in complete sentences for best accuracy
- Use /voice-to-claude:config to change model or hotkey
- Use /voice-to-claude:stop to stop the daemon
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.
- 4d ago First seen · 58 lines · 6 tokens per session scan A ea650e76f69a
start is a command published in the GitHub repository enesbasbug/voice-to-claude (10 stars, last pushed 7d ago), licensed MIT. It adds 6 tokens to every session and 712 once invoked, about $0.0000 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
wheel-to-talk-stop
Stop the Wheel to Talk backend.
wheel-to-talk-setup
Enable voice dictation and start the Wheel to Talk backend.
wheel-to-talk-status
Report whether Wheel to Talk is running and configured.
wp-seed
Seed WordPress content from demo HTML — parses sections, creates pages, imports media, populates ACF fields, builds menus, supports bilingual content.
wp-header
Build the WordPress header — responsive nav, logo, language switcher, WP menu system integration.
wp-audit
Comprehensive audit — security, SEO, accessibility, performance, best practices.