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/ongit clone --depth 1 https://github.com/leonidb/claude-code-audio-recapWrote 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/leonidb/claude-code-audio-recap/on)<a href="https://agentmods.dev/commands/leonidb/claude-code-audio-recap/on"><img src="https://agentmods.dev/badge/commands/leonidb/claude-code-audio-recap/on.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 | $0.00010 | $0.00144 |
| Opus 5 | $0.00005 | $0.00072 |
| Sonnet 5 | $0.00002 | $0.00029 |
| Haiku 4.5 | $0.00001 | $0.00014 |
Grade A, and why
on 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 3d 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:on command.
Run this bash command verbatim, then report its stdout to the user exactly as printed:
${CLAUDE_PLUGIN_ROOT}/scripts/run.sh ${CLAUDE_PLUGIN_ROOT} command --session-id "${CLAUDE_SESSION_ID}" --cwd "$PWD" on
The command persists a single boolean per CC session to ~/.claude/audio-recap/state/<session-id>.json and prints a one-line confirmation. 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.
- 3d ago First seen · 14 lines · 10 tokens per session scan A 9ce4fd975a6d
on is a command published in the GitHub repository leonidb/claude-code-audio-recap (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 10 tokens to every session and 144 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
Read your immediately preceding response aloud — local mode (verbatim, mechanical) or llm mode (LLM-written spoken summary).
dock
Automate macOS Dock interactions via peekaboo dock.
space
Manage macOS Spaces via peekaboo space.
archive-mail
歸檔指定聯絡人的 Apple Mail 郵件到 Markdown 檔案.
Manage macOS Mail.app - list, read, search, send, reply, update flags, move, delete, and verify sender authentication.
reminders
Manage macOS reminders - list, search, create, complete, update, delete with filtering and batch operations.