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/coltonbearden/carrelWrote 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/coltonbearden/carrel/audiobook)<a href="https://agentmods.dev/commands/coltonbearden/carrel/audiobook"><img src="https://agentmods.dev/badge/commands/coltonbearden/carrel/audiobook/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/coltonbearden/carrel/audiobook"><img src="https://agentmods.dev/badge/commands/coltonbearden/carrel/audiobook.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 | $0.00026 | $0.00764 |
| Opus 5.5 | $0.00010 | $0.00306 |
| Sonnet 5.5 | $0.00005 | $0.00153 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
audiobook 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 1mo 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
Create an audiobook from: $ARGUMENTS
Run the carrel CLI via Bash. Map the user's request onto the real flags in the --help block below (regenerated from the CLI by scripts/sync_plugins.py; if the installed carrel audiobook --help differs, trust the installed version — never invent flags):
Usage: carrel audiobook [OPTIONS] SRC
Narrate SRC (txt, md, pdf) into an audiobook.
Markdown is stripped for speech: headings become spoken chapter announcements, code blocks become
"[code omitted]", links read their text. mp3/ogg need ffmpeg; --format wav works with espeak-ng
alone. Existing outputs are never overwritten without --force. With --json, prints {src, outputs,
engine, duration_s, chars}.
Options:
-o, --output FILE Output audio file (default: SRC with audio extension).
--voice TEXT Voice: espeak voice name, piper model path, or edge-tts voice.
--rate INTEGER RANGE Speech rate in words per minute. [default: 170; 80<=x<=450]
--engine [auto|espeak|piper|edge-tts]
TTS engine; auto prefers piper > edge-tts > espeak-ng. [default:
auto]
--split-chapters One file per chapter (markdown H1/H2, or the PDF outline).
--force Overwrite existing output files.
--format [mp3|ogg|wav] Audio format (default: from -o extension, else mp3).
--json Machine-readable JSON output.
--help Show this message and exit.
Note: --json is a global flag and may come before the subcommand.
SRC: txt/md/pdf — text is extracted automatically; markdown headings become spoken chapter markers and code blocks are skipped.--engine(default auto): auto prefers piper > edge-tts > espeak-ng, whichever is installed.--split-chapters: one output file per H1/H2 chapter (md, or pdf with an outline).--format(default mp3): mp3/ogg need ffmpeg;wavworks with espeak-ng alone.--rate: words per minute (80–450);--voice: engine-specific voice name or piper model path.--force: only when the user explicitly wants an existing output overwritten.
Interpret the JSON result {src, outputs, engine, duration_s, chars}: tell the user which engine spoke, the output file(s), and the duration. Exit code 3 means a TTS engine or ffmpeg is missing — relay the install hint from stderr verbatim — it names the package for the user's own platform (espeak-ng is the minimal engine; suggest --format wav when ffmpeg is absent).
Requires the carrel CLI on PATH. If carrel is not found, tell the user to install it with uv tool install carrel (see the repo's INSTALL notes), or run it as uv run carrel ... from the carrel repo root.
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.
- 1mo ago Changed scan B → A 9c293a0c109a
- 1mo ago Changed · +24 lines 97a31e18d751
- 1mo ago Changed 1305ca7d5f86
- 1mo ago First seen · 26 lines · 26 tokens per session scan B 41ed48c499af
audiobook is a command published in the GitHub repository coltonbearden/carrel (2 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 764 once invoked, about $0.0001 per session on Opus 5.5. 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
add-agent
Add a new sub-agent to the current plugin for specialized tasks.
add-command
Add a new slash command to the current plugin.
add-skill
Add a new Skill to the current plugin with proper structure.
init
Scaffold a new Claude Code plugin with standard structure and starter files.
hello
Greet the user with a friendly, personalized message.
run-quality-gates
Run code quality checks (lint, format, type check, tests).