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/leonidb/claude-code-audio-recap/repeatgit clone --depth 1 https://github.com/leonidb/claude-code-audio-recapWhat 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 | $0.00028 | $0.00225 |
| Opus 5 | $0.00014 | $0.00112 |
| Sonnet 5 | $0.00006 | $0.00045 |
| Haiku 4.5 | $0.00003 | $0.00022 |
Grade A, and why
repeat 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 2d 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
The user invoked the Audio Recap plugin's /audio-recap:repeat command.
Run this bash command verbatim, then report its stdout to the user exactly as printed (it is usually empty — /audio-recap:repeat produces audio, not text):
${CLAUDE_PLUGIN_ROOT}/scripts/run.sh ${CLAUDE_PLUGIN_ROOT} repeat --session-id "${CLAUDE_SESSION_ID}" --cwd "$PWD"
/audio-recap:repeat is state-independent: it works whether Audio Recap is on or off. On a cache hit (any prior turn this session was narrated) it replays instantly. On a cache miss it generates on demand from the latest assistant turn in CC's session transcript, then caches and speaks the result. Empty transcript → audible "nothing to repeat" cue.
Do not interpret, rephrase, or add commentary to its output — quote it to the user directly.
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.
- 2d ago First seen · 16 lines · 28 tokens per session scan A cc6ad0d29669
repeat is a command published in the GitHub repository leonidb/claude-code-audio-recap (7 stars, last pushed 28d ago), licensed Apache-2.0. It adds 28 tokens to every session and 225 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
speak-voice
Get, set, list, or reset the TTS voice used by all speech output (macOS say or Linux espeak-ng).
tts-status
Show current TTS plugin status.
tts-setup
Set up TTS with a provider (elevenlabs, openai, google, amazon, azure, edge, kitten, tada, fish, gemini, local).
tts-off
Disable text-to-speech for Claude responses.
tts-on
Enable text-to-speech for Claude responses.
tts-stop
Stop TTS playback immediately.