What is separate-vocals-skill AGENTS.md?

An audio-processing tool that separates a recording into a human-vocals track and a background music or instruments track. It uses Meta’s Demucs machine-learning model and accepts common audio files such as MP3, WAV, FLAC, and OGG.

It helps create an isolated voice track or an accompaniment track from an audio file, producing two WAV files for further editing or use.

It removes the need to isolate vocals manually when you need speech or singing separated from the rest of a recording.

How sojipi/separate-vocals-skill configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to sojipi/separate-vocals-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/sojipi/separate-vocals-skill/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/sojipi/separate-vocals-skill

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sojipi/separate-vocals-skill/agents-md/github.svg)](https://agentmods.dev/instructions/sojipi/separate-vocals-skill/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/sojipi/separate-vocals-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/sojipi/separate-vocals-skill/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sojipi/separate-vocals-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/sojipi/separate-vocals-skill/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 546 This file is loaded in full into every session.

When invoked 546 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00546	$0.00546
Opus 5	$0.00273	$0.00273
Sonnet 5	$0.00109	$0.00109
Haiku 4.5	$0.00055	$0.00055

Measured 9d ago against content hash ed5c9441e6f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

separate-vocals-skill AGENTS.md 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 9d 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.

AGENTS.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Separate Vocals — Agent Instructions

Audio vocal separation skill using Meta's Hybrid Transformer Demucs model. Separates human voice from background music/instruments.

Quick Start

# Install dependencies
pip install demucs soundfile torch torchaudio

# Run separation
python separate_vocals.py <audio_file>

Project Structure

separate-vocals-skill/
├── separate_vocals.py          # Core script — CLI entry point
├── commands/
│   └── separate-vocals.md      # Slash command definition
├── AGENTS.md                   # This file — universal agent instructions
├── CLAUDE.md                   # Claude Code specific instructions
├── CODEX.md                    # OpenAI Codex specific instructions
├── requirements.txt            # Python dependencies
├── package.json                # Project metadata
└── LICENSE                     # MIT License

How It Works

Input: An audio file (MP3, WAV, FLAC, OGG, etc.)
Model: htdemucs — Meta's Hybrid Transformer Demucs
Processing: Loads audio via soundfile (no FFmpeg needed), runs the Demucs neural network to separate sources
Output: Two WAV files:
- <name>_vocals.wav — isolated human voice
- <name>_background.wav — everything else (instruments, music)

Agent Workflow

When a user asks to separate vocals from an audio file:

Verify dependencies: Run python -c "import demucs, soundfile, torch" to check. If missing, install with pip install demucs soundfile torch torchaudio
Run separation: python separate_vocals.py "<file_path>"
Report results: Tell the user the output file paths

Optional Arguments

--output-dir / -o: Specify output directory (default: same as input file)
--model / -m: Specify Demucs model (default: htdemucs). Other options: htdemucs_ft, mdx_extra

Technical Notes

Uses soundfile instead of torchaudio to avoid FFmpeg dependency issues (especially on Windows)
Processing runs on CPU by default; large files may take several minutes
Supports any audio format that soundfile can read (WAV, FLAC, OGG, etc.; MP3 via libsndfile)
Output is always WAV format, 44100Hz, stereo

Read the full file on GitHub · 58 lines

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.

9d ago First seen · 58 lines · 546 tokens per session scan A ed5c9441e6f9

Subscribe to this mod's changes

separate-vocals-skill AGENTS.md is an instructions file published in the GitHub repository sojipi/separate-vocals-skill (2 stars, last pushed 4mo ago), licensed MIT. It adds 546 tokens to every session, about $0.0027 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.

Creative and media

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

separate-vocals-skill: Instructions file for Codex