Borrowing it
Nothing to install: this file belongs to frankxai/Starlight-Intelligence-System. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/frankxai/Starlight-Intelligence-System/main/.claude/commands/music-canvas.mdgit clone --depth 1 https://github.com/frankxai/Starlight-Intelligence-SystemWrote 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/commands/frankxai/starlight-intelligence-system/music-canvas)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/music-canvas"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/music-canvas/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/commands/frankxai/starlight-intelligence-system/music-canvas"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/music-canvas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00021 | $0.00671 |
| Opus 5 | $0.00010 | $0.00336 |
| Sonnet 5 | $0.00004 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
music-canvas 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/music-canvas — Spotify Canvas + Reel/Short generation
Generate the short-form video assets (Spotify Canvas, YT Short, IG Reel, TikTok cut) for a song. Persona-DNA + label-DNA locked. Programmatic via Remotion.
Usage
/music-canvas frank-riemer_20260501_threshold
/music-canvas pulse-01_20260520_evening-journal
Arguments
- song-id (required) — song in catalog (draft or released)
Behavior
Invokes music-is/asset-render skill (Senior tier, Sonnet 4.6 orchestrate) → external engines.
Output formats
| Format | Specs | Engine | Use |
|---|---|---|---|
| Spotify Canvas | 9:16 1080×1920 MP4 ≤8MB, 3-8s loop | Remotion (programmatic per-persona template) | Spotify-for-Artists upload |
| YT Short | 9:16 1080×1920 MP4, 15-60s | Remotion or Seedance 2 | Claw-YT drop |
| IG Reel | 9:16 1080×1920 MP4, 15-60s | Remotion or Seedance 2 | Claw-IG drop |
| TikTok cut | 9:16 1080×1920 MP4, 15-30s with sound-grab hook | Remotion or Seedance 2 | Claw-TT drop |
Generation pattern
- Pull persona visual DNA + label visual DNA + song metadata
- For each format, compose engine prompt (3-layer: label DNA + persona DNA + song-specific)
- Render via engine
- DNA-check (auto-classifier against reference image set)
- Auto-retry up to 3x on DNA failure; escalate to Frank
- Land in
catalog/<state>/<song-id>/assets/ - Update catalog row asset paths
Refusals
- Render without persona canon reference
- Asset that violates label visual DNA
- Asset that violates persona visual DNA
- Engine output claimed as human-painted/photographed
Cost discipline
- Canvas regeneration: max 5 iterations per song (Remotion is cheap; iteration is cheap)
- YT Short / IG Reel / TikTok via Seedance: max 3 iterations per song
- Total per-song short-form asset cost cap: $X (per persona's monetization stack ROI)
Composes with
/music-release— Canvas required for gate-pass per release-gate skill/music-amplify— Reel/Short/TikTok cuts feed into Claw drops- Persona CANON visual DNA — DNA reference set authoritative
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 · 67 lines · 21 tokens per session scan A 16491b24f4f8
music-canvas is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 671 once invoked, about $0.0001 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 commands, from other repositories
memories
View and manage learned memories.
mpm-session-resume
Load context from paused session.
forget
Delete specific memories.
learn
Add new learning to memory.
gbu-retro
Post-session retrospective — harvest this session's lessons into durable doctrine.
agentic-jujutsu
The learning backbone of ACOS. Based on ruvnet's agentic-jujutsu (v2.3.6, MIT), customized for ACOS.