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.
git 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-song)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/music-song"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/music-song/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-song"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/music-song.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 | $0.00014 | $0.00506 |
| Opus 5 | $0.00007 | $0.00253 |
| Sonnet 5 | $0.00003 | $0.00101 |
| Haiku 4.5 | $0.00001 | $0.00051 |
Grade A, and why
music-song 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.
What it actually says
/music-song — Suno URL → catalog draft
Capture a Suno-generated song into the Music IS catalog as a draft row, queue asset render, register in label/persona indexes.
Usage
/music-song https://suno.com/song/abc123 frank-riemer evening-piano
/music-song https://suno.com/song/xyz789 pulse-01 lo-fi-evening
Arguments
- suno-url (required) — Suno song URL or extension share URL
- persona (required) — persona codename; rejection if not provided or invalid
- intent (optional) — short tag like "evening-journal", "gym-peak", "score-grade"
Behavior
Invokes music-is/song-intake skill (Mechanical tier, Haiku 4.5):
- Validates persona (must be active in
verticals/music-is/labels/<label>/personas/<persona>/CANON.md) - Extracts Suno metadata (title, prompt, BPM, duration, structure tags)
- Generates song-id:
<persona>_<YYYYMMDD>_<short-slug> - Writes
catalog/master.csvdraft row +catalog/draft/<song-id>.md - Registers in persona's
releases-index.md - Dispatches
music-producer(Sonnet 4.6) to queue asset render bundle (cover + motion + Canvas; +Higgsfield for cinematic-grade labels) - Returns: catalog row written, draft md path, asset queue status, next-step suggestion
Refusals
- No persona attribution → orphan track refused
- Persona not registered in active LABELS.md
- Engine not declared in STACK.md L2
- Vocal track using non-Frank cloned voice without consent doc on file
- Duplicate intake (idempotent; use update path for revisions)
Composes with
/music-suno-prompt— generate the prompt that produces the URL/music-release— gate the song after asset bundle complete
Built on SIP — /music-song · Mechanical tier · idempotent · persona-attribution-required
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 · 52 lines · 14 tokens per session scan A 745b91328a02
music-song is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 506 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.