A tool for generating songs and instrumental music through the Suno music-generation service. It can also create background tracks designed to sit underneath speech.

Use it to make songs, soundtracks, neutral background music, and multiple variations of an idea for videos, podcasts, voiceovers, or explainers.

It removes the need to compose or source every track manually when a description is enough to start. It is particularly useful when music should support narration without competing with the speaker.

suno-music — Skill by howdeploy

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.

agentmods

npx agentmods add skills/howdeploy/kisa-stack/suno-music

Any agent

npx skills add howdeploy/kisa-stack --skill suno-music

Clone the repo

git clone --depth 1 https://github.com/howdeploy/kisa-stack

Made for: Claude Code, Codex.

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,666 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. Scan, not verified.

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	$0.00027	$0.02666
Opus 5	$0.00014	$0.01333
Sonnet 5	$0.00005	$0.00533
Haiku 4.5	$0.00003	$0.00267

Measured 3d ago against content hash 8018a4cd2971, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

suno-music scanned grade A with 1 finding 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.

The scan reads SKILL.md. This mod also ships 3 executable files (generate.py, suno.js, test.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Если URL из EvoLink/Suno media CDN дает 403 при скачивании через `urllib` или похожий голый HTTP-клиент, повтори скачивание через `curl -L --fail`. У этих ссылок бывают капризные CDN/redirect-пути, где `curl` проходит

skills/suno-music/SKILL.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Suno Music Generation Skill

Примечание по среде. Скилл писался в среде Hermes: отправка в Telegram и формат MEDIA:/path — ее конвенции доставки. В Claude Code / Codex просто сохрани файл и отдай пользователю абсолютный путь.

Описание

Генерация музыки через EvoLink Suno API. Подходит и для обычных треков по описанию, и для более точных фоновых underscore-треков под ролики, voiceover и объясняющие видео.

Когда использовать

пользователь просит создать трек или музыку
нужен нейтральный фон под ролик, подкаст, объяснялку, видеоэссе
нужно быстро получить несколько вариантов одной музыкальной идеи
упоминаются suno, музыка, трек, фон, саундтрек

Триггеры (автоматическое определение)

"создай трек"
"сгенерируй музыку" / "сделай песню"
"музыка под настроение"
"хочу послушать музыку"
"давай сделаем трек"
упоминание "suno"

Workflow (упрощенный)

Пользователь просит трек человеческим языком
Я коротко подтверждаю и сразу генерирую
Собираю промпт автоматически или вручную, если нужен более точный результат
Отправляю запрос в API
Жду завершения задачи и скачиваю файл
Если прямой Telegram target настроен — отправляю MP3
Если target не настроен или встроенная отправка недоступна — возвращаю файл через MEDIA:/absolute/path

API

Base URL: https://api.evolink.ai/v1
Endpoint: /audios/generations
Auth: Bearer token в заголовке
API Key: хранится в файле .env в директории скилла (см. .env.example)

Базовый workflow

Получаю запрос пользователя
Собираю промпт: жанр, настроение, BPM, инструменты, ограничения
POST на /v1/audios/generations
Получаю task_id
Polling /v1/tasks/{task_id} каждые 5 секунд
Когда status == "completed" — скачиваю audio URL
Возвращаю готовый файл пользователю

Параметры генерации

model: suno-v5 (по умолчанию; при необходимости можно пробовать другие)
prompt: текстовое описание трека
custom: true/false
lyrics: текст песни, если нужна песня, а не инструментал

Read the full file on GitHub · 209 lines

Files

What ships with it

9 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.

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.

3d ago First seen · 209 lines · 27 tokens per session scan A 8018a4cd2971

Subscribe to this mod's changes

suno-music is a skill published in the GitHub repository howdeploy/kisa-stack (23 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 2,666 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Creative and media audio evolink generation music suno telegram

minimax-music-gen

Use this skill when the user wants to generate music using MiniMax's Music Generation API. Supports text-to-music with lyrics, instrumental generation, and music cover. Use when 用户提到生成音乐、文生音乐、 AI 作曲、创作歌曲、写一首歌、音乐生成、AI 音乐、MiniMax 音乐、作词作曲、纯音乐、伴奏、翻唱、cover。.

desirecore/market · 95 tokens

videoagent-audio-studio

Tired of juggling multiple audio APIs? This skill gives you one-command access to TTS, music generation, sound effects, and voice cloning. Use when you want to generate any audio without managing multiple API keys.

pexoai/pexo-skills · 50 tokens

ComfyUI on a rented GPU: setup, API, Telegram

Use when the user wants to run ComfyUI image/video generation on a rented remote GPU instead of paid API subscriptions: rent a GPU box, bootstrap the stack, connect the agent over SSH, drive workflows via the ComfyUI API, and deliver results to Telegram.

howdeploy/deploychan_mcp · 68 tokens

suno-music