claude-music-export

claude-music-export is a skill for Claude Code from AgriciDaniel/claude-music. It costs 58 tokens per session (775 once invoked), scanned A, original, MIT.

A guide for preparing finished music files for different services and uses, including streaming platforms, video sites, social media, podcasts, CDs, archives, and the web.

In plain words
What is it for?
It helps convert audio with FFmpeg, adjust loudness, choose formats and bit rates, and add metadata for services such as Spotify, Apple Music, YouTube, TikTok, and podcasts.
Why use it?
It removes the need to remember each destination’s audio format, volume level, sample rate, and file-size requirements.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Part of the claude-music plugin — 12 skills, 1 agent shipped together

Good fit It helps convert audio with FFmpeg, adjust loudness, choose formats and bit rates, and add metadata for services such as Spotify, Apple Music, YouTube, TikTok, and podcasts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agricidaniel/claude-music/claude-music-export
Install

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.

Any agent
npx skills add AgriciDaniel/claude-music --skill claude-music-export
Clone the repo
git clone --depth 1 https://github.com/AgriciDaniel/claude-music

Made for: Claude Code.

Or install claude-music, the plugin that ships this one along with the rest of its 12 skills, 1 agent.

Wrote 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.

agentmods badge for claude-music-export

README.md
[![agentmods](https://agentmods.dev/badge/skills/agricidaniel/claude-music/claude-music-export/github.svg)](https://agentmods.dev/skills/agricidaniel/claude-music/claude-music-export)
Your own site
<a href="https://agentmods.dev/skills/agricidaniel/claude-music/claude-music-export"><img src="https://agentmods.dev/badge/skills/agricidaniel/claude-music/claude-music-export/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.

agentmods 80×15 button for claude-music-export

Your own site · 80×15
<a href="https://agentmods.dev/skills/agricidaniel/claude-music/claude-music-export"><img src="https://agentmods.dev/badge/skills/agricidaniel/claude-music/claude-music-export.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 775 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.00775
Opus 5.5 $0.00023 $0.00310
Sonnet 5.5 $0.00012 $0.00155
Haiku 4.5 $0.00006 $0.00077

Measured 1mo ago against content hash 572091d60b9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-music-export 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.

skills/claude-music-export/SKILL.md · 91 lines

What it actually says

claude-music-export — Platform Export

Platform Presets

Spotify / Apple Music / Streaming

ffmpeg -i input.flac -af loudnorm=I=-14:TP=-1:LRA=11:print_format=summary \
  -ar 44100 -sample_fmt s16 -c:a flac output_spotify.flac

YouTube

ffmpeg -i input.flac -af loudnorm=I=-14:TP=-1:LRA=11 \
  -c:a libmp3lame -b:a 320k -ar 48000 output_youtube.mp3

TikTok / Instagram Reels

ffmpeg -i input.flac -af loudnorm=I=-14:TP=-1:LRA=11 \
  -c:a aac -b:a 256k -ar 44100 output_tiktok.m4a

Podcast

ffmpeg -i input.flac -af loudnorm=I=-16:TP=-1:LRA=11 \
  -c:a libmp3lame -b:a 192k -ar 44100 -ac 1 output_podcast.mp3

CD Quality

ffmpeg -i input.flac -ar 44100 -sample_fmt s16 -c:a pcm_s16le output_cd.wav

Archive (Lossless)

ffmpeg -i input.flac -c:a flac -compression_level 8 output_archive.flac

Web (Small file)

ffmpeg -i input.flac -c:a libopus -b:a 128k output_web.opus

Loudness Targets

Platform LUFS True Peak Notes
Spotify -14 -1 dBTP Auto-normalized on ingest
Apple Music -16 -1 dBTP Sound Check normalization
YouTube -14 -1 dBTP Loudness normalized
TikTok -14 -1 dBTP
Podcast -16 to -18 -1 dBTP Mono recommended
CD ~-9 to -12 0 dBTP No normalization standard

Metadata Tagging

ffmpeg -i input.flac \
  -metadata title="Song Title" \
  -metadata artist="Artist Name" \
  -metadata album="Album Name" \
  -metadata date="2026" \
  -metadata genre="Pop" \
  -metadata comment="Generated with ACE-Step 1.5" \
  -c:a copy output_tagged.flac

Batch Export

For exporting to multiple platforms at once, run commands sequentially:

# Export for all major platforms
for PLATFORM in spotify youtube tiktok podcast; do
  bash ~/.claude/skills/claude-music/scripts/music_export.sh "$PLATFORM" input.flac
done
Changes

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.

  1. 1mo ago First seen · 91 lines · 58 tokens per session scan A 572091d60b9e

Subscribe to this mod's changes

claude-music-export is a skill published in the GitHub repository AgriciDaniel/claude-music (86 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 775 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

ace-step-studio

Drive ACE-Step Studio on this computer through its MCP server - write and make songs with ACE-Step 1.5 (caption, lyrics, metadata), let its own language model plan or listen to a song, make covers, remixes, repaints and stems of a track, manage the library, draw covers, split stems, turn any track into MIDI, time…

timoncool/ACE-Step-Studio · 152 tokens

suno-music

Use Suno through Ace Data Cloud in goose for Suno music, lyrics and covers. Use the installed service MCP tools; query the original task ID after generation. This plugin is maintained by Ace Data Cloud, not the service brand's official plugin.

AceDataCloud/SunoMCP · 55 tokens

yinchao-ai-music

An AI music creation tool for making complete songs or background music from text, lyrics, or a reference recording. It can also continue an existing song or write lyrics alone when requested.

yinhcao/yinchao-ai-music-skill · 144 tokens

suno-songsmith

Turn a song or album idea into release-ready Suno v6 material: a precise Style prompt, structured lyrics with directed section tags, a title, model and slider settings, and paste-ready edit commands for fixing the result — in clean copy-paste blocks that sound human, not generic AI. Use whenever the user wants to make…

RealBombi/suno-songsmith · 208 tokens

patent-map

A tool for making a visual map of stored patent case notes in an Obsidian vault. Obsidian is a note-taking application that stores linked text files.

handsomestWei/patent-disclosure-skill · 48 tokens

autoreview

Structured code review through the shared OpenClaw agent-skills installation.

openclaw/clawhub · 17 tokens