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/jason-c-dev/claude-code-speak/speech-stopgit clone --depth 1 https://github.com/jason-c-dev/claude-code-speakWhat 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 | $0.00015 | $0.00249 |
| Opus 5 | $0.00008 | $0.00125 |
| Sonnet 5 | $0.00003 | $0.00050 |
| Haiku 4.5 | $0.00002 | $0.00025 |
Grade A, and why
speech-stop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Stop any in-flight Claude Speech audio for the current session. The plugin's
playback is per-session, so we need to clear the queue and SIGTERM the player
process (and its afplay child) for this Claude Code session id.
Run this Bash command and report the result back to the user:
SESSION_FILE=$(ls -t ~/.claude/voice/state/*.json 2>/dev/null | head -1)
if [ -z "$SESSION_FILE" ]; then
echo "No active voice session found."
exit 0
fi
python3 -c "
import sys
sys.path.insert(0, '${CLAUDE_PLUGIN_ROOT}')
from scripts.playback import clear_and_kill
from pathlib import Path
import json
sid = json.load(open('${SESSION_FILE}'))['session_id']
clear_and_kill(sid)
print(f'Stopped voice for session {sid}.')
"
Reply briefly to the user with whatever was printed (e.g. "Stopped voice for session abc123." or "No active voice session found."). Do not add commentary.
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 · 31 lines · 15 tokens per session scan A 74dc2218cca0
speech-stop is a command published in the GitHub repository jason-c-dev/claude-code-speak (2 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 249 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
video-maker
코드로 영상을 만들어요. React 기반 Remotion으로 프로그래밍 영상 제작.
music
Control background music generation.
model
Switch TTS model (no arg opens a picker).
provider
Switch TTS provider (no arg opens a picker).
pn-delight
Add purposeful moments of joy, motion, and personality. Use when the design is correct and complete but feels flat and lifeless.
setup-elevenlabs.es
Command "setup-elevenlabs.es" from minicoohei/ai-agent-camp, covering configuración de la api de elevenlabs, step 0: verificar el progreso de configuración, lo que hará en esta sesión, verificación de preparación and step 1: abrir elevenlabs en el navegador.