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 skills add coroboros/agent-skills --skill audio-loopgit clone --depth 1 https://github.com/coroboros/agent-skillsWrote 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/skills/coroboros/agent-skills/audio-loop)<a href="https://agentmods.dev/skills/coroboros/agent-skills/audio-loop"><img src="https://agentmods.dev/badge/skills/coroboros/agent-skills/audio-loop/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/skills/coroboros/agent-skills/audio-loop"><img src="https://agentmods.dev/badge/skills/coroboros/agent-skills/audio-loop.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 | $0.00046 | $0.02462 |
| Opus 5.5 | $0.00018 | $0.00985 |
| Sonnet 5.5 | $0.00009 | $0.00492 |
| Haiku 4.5 | $0.00005 | $0.00246 |
Grade B, and why
audio-loop scanned grade B with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
`command -v ffmpeg ffprobe`. Missing → stop and ask the user to install (macOS: `brew install ffmpeg`, Debian/Ubuntu: `sudo apt install ffmpeg`). Never auto-install. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
bufferPromise = fetch(AUDIO_URL) How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audio Loop
Prepare a source that already joins continuously for Web Audio playback: optionally balance stereo, normalize loudness and encode FLAC. The pipeline does not repair source discontinuities; inspect the join before promising a seamless result.
All ffmpeg work happens in scripts/audio-loop.sh — this skill validates the source, orchestrates the pipeline, and turns the script's summary into a report plus a ready-to-paste JS snippet.
Parameters
| Flag | Default | Description |
|---|---|---|
-t <LUFS> |
-28 |
Integrated loudness target (ambient web default) |
-v <0..1> |
0.6 |
Target volume baked into the emitted JS snippet |
-o <dir> |
input dir | Output directory |
-s |
off | Save to ~/.agents/output/{project}/audio-loop/{slug}/ |
-S |
off | Force no-save |
-B |
off | Disable stereo balance auto-correction |
Where each flag is handled. -t, -o, and -B pass through to scripts/audio-loop.sh. -v is skill-only — the agent reads it from $ARGUMENTS and interpolates it into the TARGET constant of the emitted JS snippet; the script never sees it. -s / -S follow the repo save-mode convention — the agent translates -s into an -o <save_path> passed to the script, where <save_path> is ~/.agents/output/{project}/audio-loop/{slug}/ ({project} = kebab-cased basename of the git toplevel, else cwd; create it $HOME-expanded, report the fully-expanded absolute path — no tilde, no magic).
Deliberately no crossfade flag. If the source WAV has a real sample-level discontinuity at the loop boundary, that's source editing — outside this skill's scope. If the user is hearing a bump with FLAC + Web Audio, see Diagnostic by negative result below.
Workflow
1. Validate tools
command -v ffmpeg ffprobe. Missing → stop and ask the user to install (macOS: brew install ffmpeg, Debian/Ubuntu: sudo apt install ffmpeg). Never auto-install.
2. Probe the source
The script reads duration, sample rate, channel count, and per-channel RMS via astats. Surface these early — the user sees the starting point before any processing.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · -3 lines · -169 tokens per session ffb906434cba
- 1mo ago First seen · 170 lines · 215 tokens per session scan B 27b2316a3267
audio-loop is a skill published in the GitHub repository coroboros/agent-skills (4 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 2,462 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
safe-refactor
Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.