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 novoads/agent-skills --skill music-mixgit clone --depth 1 https://github.com/novoads/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/novoads/agent-skills/music-mix)<a href="https://agentmods.dev/skills/novoads/agent-skills/music-mix"><img src="https://agentmods.dev/badge/skills/novoads/agent-skills/music-mix/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/novoads/agent-skills/music-mix"><img src="https://agentmods.dev/badge/skills/novoads/agent-skills/music-mix.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 | $0.00127 | $0.02196 |
| Opus 5 | $0.00063 | $0.01098 |
| Sonnet 5 | $0.00025 | $0.00439 |
| Haiku 4.5 | $0.00013 | $0.00220 |
Grade A, and why
music-mix 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 11d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Music mix
Puts a music bed under a finished video. The bed is trimmed to the video's exact duration, faded out at the tail, and ducked under the voice. This is the last step of the pack: base video → b-roll overlay → burned captions → music.
Mixing mechanics live entirely in scripts/music_mix.py. This file is judgment only —
when to enter, what track to pick, where the music comes from, what the user sees.
Entry condition
A finished video the user has signed off on. Captions already burned in is the
preferred input, because music is genuinely the last thing that happens. That is safe
because the script copies the video stream packet for packet (-c:v copy) and verifies
afterwards that the output's video packets hash identical to the input's — so burned
captions come through bit-exact, not "re-encoded but probably fine".
If the cut is still moving, wait. Remixing is cheap; re-rendering the pipeline is not.
Track judgment
- Match the genre to the ad's mood, not to your taste. Calm skincare and a punchy supplement ad do not want the same bed. Read the script's tone first.
- Lofi is the default — it is what the reference edit used, and it sits under a talking head without competing with it. Depart from it deliberately, and say why.
- Always produce 2–3 named variants. The reference edit shipped a
final-mixesfolder withlofi-jazzyandlofi-warmof the same cut. Vary the track or--music-gain, name them for what they are, and let the user pick — each extra mix is one ffmpeg pass and no credits. - Instrumental only. Lyrics compete with the voiceover for the same attention.
Sourcing the music
REST key required. A Novoads MCP connector is not a substitute. If
NOVOADS_API_KEYis missing or still the placeholder, stop before any generation work and tell the user: "Before continuing, create an API key at https://novoads.ai/dashboard/settings?tab=api and paste it into.env." That holds even whenmcp__novoads__*tools are connected and authenticated in the session. Never callmcp__novoads__*tools from this repo's workflows: they are a different surface with different behavior, including the units they quote costs in. Repo installs verify with./scripts/check-novoads-env.sh; a solo install checksNOVOADS_API_KEYin the environment.
What ships with it
4 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.
- 11d ago First seen · 149 lines · 127 tokens per session scan A 3dfc32cbcb27
music-mix is a skill published in the GitHub repository novoads/agent-skills (14 stars, last pushed today), licensed MIT. It adds 127 tokens to every session and 2,196 once invoked, about $0.0006 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.
Other skills, from other repositories
video-shotcraft
Create cinematic product videos from shot recipe cards, a validated template, and code/audio assets (Remotion + real page screenshots + 2.5D camera moves + beat-synced cuts + sound design). Use when the user asks to turn a frontend project or webpage into a product video, says "use video-shotcraft to make a…
xiaohongshu-auto-posting
Automates the complete Xiaohongshu (XHS / Little Red Book) content operation workflow: pain-point topic collection → style case collection → topic selection → content writing → publishing → performance tracking. Use when user mentions xiaohongshu auto posting, xhs auto post, little red book posting, xiaohongshu post…
tiktok-shop-branding
Brand building and positioning on TikTok Shop. Brand identity development, content pillars, community engagement, brand storytelling, and authenticity strategies. Use when the user asks about TikTok branding, brand building, brand identity, or brand positioning on TikTok.
tiktok-shop-content-strategy
TikTok Shop content creation strategy and planning. Trending formats, viral hooks, product showcasing, hashtag strategy, and content calendar development. Use when the user asks about TikTok content strategy, viral content creation, TikTok marketing, or content planning.
ppt-design-skill
Design, generate, review, and revise editable PowerPoint presentations through a rigorous brief-to-PNG workflow using the public pptx-designer Python library.
etsy-digital-products
Digital product creation and selling — templates, printables, planners, digital art, delivery setup.