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 calesthio/generative-media-skills --skill suno-musicgit clone --depth 1 https://github.com/calesthio/generative-media-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/calesthio/generative-media-skills/suno-music)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/suno-music"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/suno-music/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/calesthio/generative-media-skills/suno-music"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/suno-music.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00176 | $0.05637 |
| Opus 5 | $0.00088 | $0.02818 |
| Sonnet 5 | $0.00035 | $0.01127 |
| Haiku 4.5 | $0.00018 | $0.00564 |
Grade A, and why
suno-music 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.
How it starts
The opening of the file, as written. The whole thing — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Suno music generation and rights advisory
Suno is a text-to-music service that generates full songs (vocals + instrumental) from a style description and optional lyrics, plus editing tools (extend, cover, remaster, stem separation, a DAW-style Studio). This skill covers two things a production agent must get right at the same time: making good music with the current models and advising accurately on the rights, licensing, and legal reality of using that music commercially.
The rights half is not an appendix. As of mid-2026 the single most common way to give a production team bad advice is to treat Suno output as freely ownable, copyrightable, and API-accessible. Read the "Rights, licensing, and legal reality" section before advising on any commercial or distribution use.
Evidence labels used below
- [Documented] — stated in Suno's own docs, terms, help center, or blog, or in a primary legal/press source, with a URL in Sources.
- [First-party claim] — Suno's own marketing/announcement language, reported as a claim rather than an independently verified fact.
- [Heuristic] — production practice inferred from how the tools behave; useful defaults, not guarantees.
Volatility warning. Models, tiers, prices, terms, litigation status, and API access change fast. Every volatile fact below carries a verification date of 2026-07-10 unless noted. Re-verify anything legal or version-specific against suno.com before relying on it.
1. Current models and what they do
[Documented] Model timeline (Suno help center "Model Timeline", verified 2026-07-10):
| Model | Released | What it added |
|---|---|---|
| V3.5 | Summer 2024 | Better structure; up to ~4 min first gen |
| V4 | Nov 2024 | Improved vocal quality; introduced Extend, Cover, Persona |
| V4.5 | May 2025 | Up to 8-min first generation; better prompt adherence; style mashups |
| V4.5+ | Jul 2025 | Add Vocals / Add Instrumental production tools |
| V5 | Sep 2025 | Higher audio fidelity, more authentic vocals; Pro/Premier only |
| V5.5 | Mar 26 2026 | Voices (record/upload your own voice), Custom Models, My Taste |
What ships with it
1 file 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.
- 9d ago First seen · 372 lines · 176 tokens per session scan A 3ee8822ec2df
suno-music is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 176 tokens to every session and 5,637 once invoked, about $0.0009 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 2026-09-03.
Other skills, from other repositories
cliptalk-cover-director
Produces evidence-backed cover candidates and reviewable cover variants for a ClipTalk video. Use when the user asks for a cover, poster frame, thumbnail, or multiple cover directions; do not use for timeline editing or social-video reframing.
cliptalk-smart-reframe
Creates a subject-aware, time-varying crop track and a review-only social-format preview from an accepted ClipTalk cut. Use for automatic vertical, square, or portrait reframing; do not use for a fixed manual crop or before content editing is accepted.
cliptalk-content-extractor
Locates and assembles source passages matching a semantic request. Use for extracting explanations, topics, quotes, demonstrations, or other specifically described content.
cliptalk-interview-editor
Produces a coherent interview edit by combining speaker discovery, topic selection, dialogue context, cleanup, subtitles, and preview. Use for interviews, podcasts, testimonials, or question-and-answer recordings.
cliptalk-shortform-hook-director
Finds and assembles a reviewable short-form cut with a strong opening hook. Use for Shorts, Reels, social clips, talking-head cutdowns, or requests for a punchier opening.
cliptalk-social-reframe-exporter
Creates a review-only 9:16, 4:5, 1:1, or 16:9 version from an existing accepted ClipTalk cut, then checks the rendered preview. Use only when a cut already exists and the user asks to adapt it for Shorts, Reels, Douyin, Xiaohongshu, WeChat Channels, or square feeds; do not use when the user still needs content found…