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-suno-prompt)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/music-suno-prompt"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/music-suno-prompt/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-suno-prompt"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/music-suno-prompt.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 | $0.00023 | $0.00640 |
| Opus 5 | $0.00012 | $0.00320 |
| Sonnet 5 | $0.00005 | $0.00128 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
music-suno-prompt 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 12d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/music-suno-prompt — Grounded Suno prompt synthesis
Generate 3-5 candidate Suno prompts grounded in (1) local knowledge corpus at verticals/music-is/knowledge/suno/, (2) target persona's canon, (3) target label's canon. No prompt is composed from training-data memory.
Usage
/music-suno-prompt "evening journaling vibe, 80 BPM, lo-fi piano, processed female vox" frank-riemer
/music-suno-prompt "gym peak-state, 165 BPM, distorted guitars, cathartic shouted vocals" razor-01
/music-suno-prompt "cinematic mythic, choral languageless, modal Lydian, build to peak" aetheria-01
Arguments
- intent (required) — one-line description of the song-target
- persona (required) — explicit codename or inferable from active context
Behavior
Invokes music-is/suno-prompt skill (Senior tier, Sonnet 4.6).
Grounding sources (read in order)
verticals/music-is/knowledge/suno/prompt-pattern-library.mdverticals/music-is/knowledge/suno/structure-tags-reference.mdverticals/music-is/knowledge/suno/genre-style-cards.mdverticals/music-is/knowledge/suno/vocal-control-recipes.mdverticals/music-is/knowledge/suno/known-bugs-workarounds.md- Label CANON visual + sound DNA
- Persona CANON sound DNA + Suno prompt anchors
Output per candidate prompt
- Composed prompt text (3-layer: style stem + intent layer + structure tags)
- Layer breakdown
- Predicted variability (which dimensions Suno is most likely to vary)
- Suggested first re-roll if first variant misses
Refusals
- Persona context missing
- Prompt violates persona-canon Suno-anchors
- Prompt targets a specific named non-Frank artist's style
- Copyright-flirting language
- Vocal-clone prompts targeting non-Frank identifiable artist without consent
Iteration discipline
- Generate 3-5 variants per intent (Suno's known variability)
- Tag each variant with seed/version metadata
- Curate-not-accept-first; every shortlisted variant gets Frank-curated A/B
- Failed variants logged to
verticals/music-is/knowledge/suno/iteration-log.md
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.
- 12d ago First seen · 68 lines · 23 tokens per session scan A b6711c1c814e
music-suno-prompt is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 640 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
harvest
You are the Prompt Harvester - an elite prompt discovery agent that scans GitHub, ArXiv, and the web for high-quality prompts, then analyzes, rates, and stores them.
frankx-ai-prompts
Add, update, and organize prompts in the FrankX.AI Prompt Library.
memories
View and manage learned memories.
metaprompt
Generate a complete, ready-to-use prompt engineered for a specific model and harness.
mpm-session-resume
Load context from paused session.
forget
Delete specific memories.