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-label-board)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/music-label-board"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/music-label-board/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-label-board"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/music-label-board.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 | $0.00635 |
| Opus 5 | $0.00010 | $0.00318 |
| Sonnet 5 | $0.00004 | $0.00127 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
music-label-board 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/music-label-board — Portfolio scorecard
Multi-persona portfolio scorecard for one or all of the four labels (frank-riemer, franks-vibes, arcanea, nona). Returns per-label rollup + per-persona detail + cross-label patterns.
Usage
/music-label-board # all four labels rollup
/music-label-board frank-riemer # single label drilldown
/music-label-board arcanea
Arguments
- label (optional) — one of:
frank-riemer,franks-vibes,arcanea,nona. Omit for cross-label rollup.
Behavior
Invokes music-is/catalog-systems skill (Mechanical tier, Haiku 4.5) → music-archivist agent.
Per-label rollup
- Active personas count + names
- Total releases (per persona, per label)
- Releases by month (last 6 months)
- Streaming revenue (Spotify-for-Artists data if integrated; manual entry fallback)
- Sync revenue (any direct deals or library payouts)
- Direct revenue (Bandcamp, Patreon if applicable)
- Royalty-graph entries count
- Amplification mesh health (active Claws, drops/week, voice-lock pass rate, frequency-cap status)
Per-persona detail
- Sound DNA snippet (at-a-glance recall)
- Releases (count + last release date + cadence health)
- Release-cadence baseline status (6-release threshold for multiplication)
- Voice-lock pass rate last 4 weeks
- Top-3 performing releases (per persona's primary metric — streams, sync placements, Bandcamp sales, etc.)
- Outstanding drafts (count + age; flags >30d stales)
Cross-label patterns (when no label arg)
- Release cadence balance across labels
- Voice-lock health across personas
- Royalty-graph aggregation (composes with Wealth IS theses if active)
- Cross-label promo opportunities (frankx.ai-driven)
Output formats
- Cowork live artifact — refreshable on open via Haiku-backed read of catalog
- Markdown summary — paste-ready
- CSV export — for Excel handoff
- (Optional) Notion sync push to AI Musicians Hub mirror
Composes with
/music-release— most recent gate-passes show in scorecard/music-amplify— amplification health metrics feed scorecardverticals/music-is/MEMORY.md— weekly hygiene reports referenced
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 · 76 lines · 21 tokens per session scan A ed6a4f129bb0
music-label-board 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 635 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.