sound-catalog-metadata-pack

sound-catalog-metadata-pack is a command for Claude Code from frankxai/Starlight-Intelligence-System. It costs 55 tokens per session (892 once invoked), scanned A, original, MIT.

A release metadata checklist containing recording and composition identifiers, contributor splits, rights information, instruments, sample and AI disclosures, sync status, alternate versions, and discography position. Metadata is the descriptive information used to identify and deliver music correctly.

In plain words
What is it for?
Use it to complete per-track release records, validate metadata, document rights and contributors, map alternate versions, and prepare distribution or final mastering.
Why use it?
It gathers the information needed for release and royalty handling in one place and checks that contributor shares total 100 percent. It also catches missing clearance, disclosure, and version details before shipping.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the starlight-intelligence-system plugin — 6 skills, 121 commands, 7 agents shipped together

Good fit Use it to complete per-track release records, validate metadata, document rights and contributors, map alternate versions, and prepare distribution or final mastering.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/frankxai/starlight-intelligence-system/sound-catalog-metadata-pack
Install

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.

Clone the repo
git clone --depth 1 https://github.com/frankxai/Starlight-Intelligence-System

Made for: Claude Code.

Or install starlight-intelligence-system, the plugin that ships this one along with the rest of its 6 skills, 121 commands, 7 agents.

Wrote 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.

agentmods badge for sound-catalog-metadata-pack

README.md
[![agentmods](https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sound-catalog-metadata-pack/github.svg)](https://agentmods.dev/commands/frankxai/starlight-intelligence-system/sound-catalog-metadata-pack)
Your own site
<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/sound-catalog-metadata-pack"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sound-catalog-metadata-pack/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.

agentmods 80×15 button for sound-catalog-metadata-pack

Your own site · 80×15
<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/sound-catalog-metadata-pack"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sound-catalog-metadata-pack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 892 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.00892
Opus 5 $0.00028 $0.00446
Sonnet 5 $0.00011 $0.00178
Haiku 4.5 $0.00006 $0.00089

Measured 9d ago against content hash ac5c6f7c5417, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

sound-catalog-metadata-pack 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 9d 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.

.claude/commands/sound-catalog-metadata-pack.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sound-catalog-metadata-pack

Load verticals/sound-intelligence/SKILL.md, agents/starlight-sound-catalog.md, skills/sound-intelligence/catalog-systems.md. Produce a complete Metadata Pack that gates release shipping.

Disclaimer (non-waivable)

Metadata pack is the substrate the catalog runs on. Royalty leakage starts here. This is system architecture, not legal advice.

Process

  1. Disclaim.
  2. Per-track field completion (DDEX-aligned where applicable).
  3. Splits totaling 100% per track.
  4. Sample clearance status per sample (never blank).
  5. AI-involvement disclosure per track.
  6. Sync-availability flag per track tied to vision boundaries.
  7. Alternate-version mapping per track.
  8. Discography position per track / release.
  9. DDEX validation pass.
  10. Save: sound-intelligence/catalog/metadata-<release-slug>-<YYYY-MM-DD>.md.
  11. Hand off: distribution submission (actual flow) or master finalization.

Output format

# Metadata Pack — <Release> — <YYYY-MM-DD>

> **Royalty leakage starts here. This is system architecture, not legal advice.**

## Per-track metadata

### Track 1: <Title>
- **ISRC:** XX-XXX-YY-ZZZZZ
- **ISWC:** T-XXXXXXXXX-X
- **Splits (totaling 100%):**
  | Contributor | Role | PRO | PRO ID | % |
  |---|---|---|---|---|
  | ... | composer | ASCAP | XXX | 50 |
  | ... | producer | BMI | XXX | 30 |
  | ... | featured artist | SESAC | XXX | 20 |
- **Instrumentation tags (DDEX):** <list>
- **Sample clearance:**
  | Sample | Source | Status |
  |---|---|---|
  | ... | ... | cleared / public domain / practitioner-original / pending / refused-uncleared |
- **AI involvement:** <none | disclosed: <description>>
- **Sync-availability flag:** <yes / no / case-by-case> — rationale: <vision-boundary respect>
- **Alternate-version map:**
  | Version | ISRC | Diff from main |
  |---|---|---|
  | instrumental | ... | no vocals |
  | sync-grade | ... | PSR ≥ 12 dB master |
- **Language:** <code or instrumental>
- **Explicit:** <yes / no>
- **Genre:** primary / secondary
- **Key:** <musical key>
- **Tempo:** <BPM>
- **Mood tags:** <list — useful for sync brief-fit>
- **Discography position:** <follows X / sets up Y>

### Track 2: ...
[same structure]

## DDEX validation
- Pass: <yes — submitted for distribution | no — fix and resubmit: <list>>

## Refusal-check
- Metadata-as-marketing-only: refused
- Single-track-into-algorithm without discography position: refused
- Sample-clearance blank: refused

**Built on SIP** — SIP v1.1.0 · Sound Intelligence — Catalog · 2026-04-26

Read the full file on GitHub · 94 lines

Changes

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.

  1. 9d ago First seen · 94 lines · 55 tokens per session scan A ac5c6f7c5417

Subscribe to this mod's changes

sound-catalog-metadata-pack is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 892 once invoked, about $0.0003 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 2026-09-03.