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-persona)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/music-persona"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/music-persona/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-persona"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/music-persona.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 | $0.00012 | $0.00770 |
| Opus 5 | $0.00006 | $0.00385 |
| Sonnet 5 | $0.00002 | $0.00154 |
| Haiku 4.5 | $0.00001 | $0.00077 |
Grade A, and why
music-persona 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/music-persona — Spawn a persona
Spawn a new persona under one of the four labels (frank-riemer, franks-vibes, arcanea, nona). Persona-keeper (Opus 4.7) gates spawn; refused if any of the 5 canon dimensions is incomplete.
Usage
/music-persona franks-vibes pulse-01
/music-persona arcanea aetheria-01
/music-persona nona razor-01
Arguments
- label (required) — one of:
frank-riemer,franks-vibes,arcanea,nona - persona-codename (required) — codename-first per DECISIONS.md D4; ships under codename for ≥3 gated releases before public-name decision
Behavior
Invokes music-is/persona-canon skill (Apex tier, Opus 4.7).
Required spawn input (refused if incomplete):
- Sound DNA — genre primary + sub-genre, reference triangle (3 named artists), harmonic vocabulary, tempo bands, vocal posture (with AI-clone disclosure if applicable), production posture, 5-10 Suno prompt anchors
- Visual DNA — color palette (max 5 hex colors), typography lock, cover composition rules, reference image set (5-15 curated), banned visual patterns
- Voice DNA — per-platform voice samples (X 140char, IG 200char, TikTok 15words, YT 60char title, SP 80char caption, fan email 300words), first-person posture, cadence, banned phrases, tone register
- Audience contract — primary listener context, demographic hypothesis, discovery surface, compounding mechanism
- Monetization stack — streaming posture, direct rail, sync posture, NFT/limited posture, royalty-cascade graph stub
On successful spawn
Scaffolds:
verticals/music-is/labels/<label>/personas/<persona>/CANON.mdverticals/music-is/labels/<label>/personas/<persona>/assets/{reference-images,voice-samples,brand-kit}/verticals/music-is/labels/<label>/personas/<persona>/social/{voice-lock-x,voice-lock-ig,voice-lock-tt,voice-lock-yt,voice-lock-sp,banned-phrases,frequency-caps}.mdverticals/music-is/labels/<label>/personas/<persona>/releases-index.md- Updates
verticals/music-is/LABELS.mdpersona allocation map - Registers persona row in
catalog/master.csv(no songs yet)
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 · 62 lines · 12 tokens per session scan A 275e87db8d99
music-persona is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 12 tokens to every session and 770 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.