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.
git clone --depth 1 https://github.com/amIT-nitb/claude-calloutWrote 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/amit-nitb/claude-callout/voice-status)<a href="https://agentmods.dev/commands/amit-nitb/claude-callout/voice-status"><img src="https://agentmods.dev/badge/commands/amit-nitb/claude-callout/voice-status/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/amit-nitb/claude-callout/voice-status"><img src="https://agentmods.dev/badge/commands/amit-nitb/claude-callout/voice-status.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00013 | $0.01126 |
| Opus 5 | $0.00006 | $0.00563 |
| Sonnet 5 | $0.00003 | $0.00225 |
| Haiku 4.5 | $0.00001 | $0.00113 |
Grade A, and why
voice-status scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Report effective voice + notification state, plus per-layer breakdown so you can see why a setting is on or off, and any active mute.
Precedence: mute > project > user > env var > built-in default.
Run this script:
USER_DIR="$HOME/.claude/callout"
PROJ_DIR="$PWD/.claude-callout"
NOW=$(date +%s)
# Mute lookup — highest priority
MUTE_SCOPE=""
MUTE_REMAINING=0
for scope_dir in "$PROJ_DIR" "$USER_DIR"; do
if [ -f "$scope_dir/mute-until" ]; then
UNTIL=$(cat "$scope_dir/mute-until" 2>/dev/null || echo 0)
if [ "$UNTIL" -gt "$NOW" ] 2>/dev/null; then
[ "$scope_dir" = "$PROJ_DIR" ] && MUTE_SCOPE="project" || MUTE_SCOPE="user"
MUTE_REMAINING=$((UNTIL - NOW))
break
fi
fi
done
resolve() {
local feature="$1" default="$2"
local proj_state="-" user_state="-" env_state="unset"
[ -f "$PROJ_DIR/${feature}-enabled" ] && proj_state="on"
[ -f "$PROJ_DIR/${feature}-disabled" ] && proj_state="off"
[ -f "$USER_DIR/${feature}-enabled" ] && user_state="on"
[ -f "$USER_DIR/${feature}-disabled" ] && user_state="off"
case "$feature" in
voice) [ -n "${CLAUDE_VOICE:-}" ] && env_state="$CLAUDE_VOICE" ;;
notify) [ -n "${CLAUDE_NOTIFY:-}" ] && env_state="$CLAUDE_NOTIFY" ;;
voice-when-focused) [ -n "${CLAUDE_VOICE_WHEN_FOCUSED:-}" ] && env_state="$CLAUDE_VOICE_WHEN_FOCUSED" ;;
esac
local effective source
# Mute silences voice/notify but does NOT change the voice-when-focused
# preference — that's a behavioral flag, not an audio gate.
if [ -n "$MUTE_SCOPE" ] && [ "$feature" != "voice-when-focused" ]; then
effective="off"; source="muted ($MUTE_SCOPE)"
elif [ "$proj_state" != "-" ]; then
effective="$proj_state"; source="project"
elif [ "$user_state" != "-" ]; then
effective="$user_state"; source="user"
elif [ "$env_state" != "unset" ]; then
effective="$env_state"; source="env"
else
effective="$default"; source="default"
fi
printf '%s|%s|%s|%s|%s\n' "$effective" "$source" "$proj_state" "$user_state" "$env_state"
}
IFS='|' read -r v_eff v_src v_proj v_user v_env <<< "$(resolve voice on)"
IFS='|' read -r n_eff n_src n_proj n_user n_env <<< "$(resolve notify on)"
IFS='|' read -r wf_eff wf_src wf_proj wf_user wf_env <<< "$(resolve voice-when-focused off)"
printf 'Voice: %s (%s)\n' "$v_eff" "$v_src"
printf 'Notifications: %s (%s)\n' "$n_eff" "$n_src"
printf 'Voice-when-focused: %s (%s)\n' "$wf_eff" "$wf_src"
printf 'Quiet hours: %s\n' "${CLAUDE_VOICE_QUIET:-none}"
printf 'Stop debounce: %ss\n' "${CLAUDE_VOICE_DEBOUNCE:-10}"
if [ -n "$MUTE_SCOPE" ]; then
M=$((MUTE_REMAINING / 60)); S=$((MUTE_REMAINING % 60))
printf 'Mute: %s scope, %dm %ds remaining\n' "$MUTE_SCOPE" "$M" "$S"
fi
echo
echo "Resolution (highest precedence wins):"
printf ' Voice project=%-3s user=%-3s env=%-5s → %s\n' "$v_proj" "$v_user" "$v_env" "$v_eff"
printf ' Notify project=%-3s user=%-3s env=%-5s → %s\n' "$n_proj" "$n_user" "$n_env" "$n_eff"
printf ' When-focused project=%-3s user=%-3s env=%-5s → %s\n' "$wf_proj" "$wf_user" "$wf_env" "$wf_eff"
echo
echo "Project state dir: $PROJ_DIR"
echo "User state dir: $USER_DIR"
Show the output to the user as-is.
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.
- 8d ago First seen · 85 lines · 13 tokens per session scan A 3728a125875e
voice-status is a command published in the GitHub repository amIT-nitb/claude-callout (1 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 1,126 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
vox
Enable or disable vox in this repo.
speak-limit
Get, set, or reset the max byte length spoken before truncating at a sentence boundary.
better-auth:add-plugin
Add a better-auth plugin to an existing project. Configures server and client plugins with proper imports.
cloudflare-r2:presigned-url
Generate presigned URLs for secure client-side uploads or downloads.
wp-tailwindify
Convert an HTML/CSS demo to Tailwind-native HTML — preserves section delimiters, maps colors to @theme variables.
design-critic
Use when you want an honest read on a design instead of encouragement. What is wrong, ranked by severity, with the reason attached. Works on a screenshot, a mockup, or a described screen.