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/sound-sync-rights-pack)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/sound-sync-rights-pack"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sound-sync-rights-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.
<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/sound-sync-rights-pack"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sound-sync-rights-pack.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 | $0.00043 | $0.01741 |
| Opus 5 | $0.00022 | $0.00870 |
| Sonnet 5 | $0.00009 | $0.00348 |
| Haiku 4.5 | $0.00004 | $0.00174 |
Grade A, and why
sound-sync-rights-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.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sound-sync-rights-pack
Load verticals/sound-intelligence/SKILL.md, verticals/sound-intelligence/SOUL.md, verticals/sound-intelligence/MEMORY.md, agents/starlight-sound-sync.md, skills/sound-intelligence/sync-licensing.md, brief-fit verdict, placement thesis, license-economics audit (or counsel-approved deal terms), per-track catalog metadata files at sound-intelligence/catalog/<track-metadata-files> if present in the practitioner's runtime vault (this path is instance-state, not substrate-shipped), and /sip-attest-audio workflow. Produce a Rights Pack — complete clearance documentation + audio asset list + attestation index. Hand off to delivery.
Disclaimer (non-waivable)
Rights documentation has legal weight. This is system architecture for assembling clearance documentation; the practitioner's music attorney signs off on every specific clearance and the final pack before delivery to licensee.
Input
$ARGUMENTS
Process
- Disclaim. Non-waivable opener.
- Verify upstream. Brief-fit PROCEED + placement-thesis tracks + license-economics counsel-approved deal terms required. Missing any → halt.
- Per-track master rights. Per track: declared master state — practitioner-owned / label-owned / co-owned with split. If label-owned or co-owned, label or co-owner consent for this placement documented. Missing consent → flag and halt.
- Per-track publishing rights. Per track: declared publishing state — practitioner-publishing / co-publishing / publisher-controlled with split. Each contributor's publishing-share documented and PRO-registered (ASCAP / BMI / SESAC / GMR for US; PRS / PPL for UK; GEMA for DE; SACEM for FR; JASRAC for JP; etc.). PRO-registration confirmation per contributor.
- Per-track sample clearances. Per sample in each track: status — cleared (with license document attached) / public-domain (with rationale) / practitioner-original / licensed-for-this-use (with license document). Any uncleared sample → halt; cannot ship rights pack with unclear sample status.
- Per-track contributor consents. Per contributor (vocalist, instrumentalist, co-writer, producer, etc.): consent for THIS specific placement documented. Generic "I consent to all sync placements" is acceptable if signed; per-placement consent is stronger and required for high-stakes placements (political, religious, controversial brand).
- AI involvement disclosure. Per track: AI used at any stage (AI-generated stems, AI-trained-on-corpus, AI-vocal-tuning beyond standard pitch correction)? Disclosed transparently. AI-vocal-impersonation status verified as never (the boundary). AI-stem-generation disclosed if used. Practitioner's AI-disclosure stance (per MEMORY.md) named.
- Delivery format. Per track: broadcast WAV (24-bit / 48kHz typical for film/TV); alternate-master if sync brief specifies; stems if deal allows / requires; instrumental version if applicable; 60-sec / 30-sec / 15-sec edits if specified.
- Attestation block per track. Run
/sip-attest-audioworkflow on each delivered audio asset; embed attestation in EXIF/XMP; ship sidecar.sip.jsonper asset; rights-pack header includes attestation index. - Cue sheet preparation. For TV / film placements: cue sheet draft (cue type, cue length, BMI/ASCAP work IDs, composer + publisher splits per cue). Counsel signs off; library / supervisor's PRO administrator finalizes.
- Final assembly. Rights pack as a single delivered package — README explaining contents + per-track folder containing audio assets + clearance documents + attestation files.
- Save. Write to
sound-intelligence/sync/rights-pack-<placement-slug>-<YYYY-MM-DD>/. - Hand off. Name exactly one next move:
- Pack complete + counsel signed → deliver to licensee with delivery confirmation.
- Clearance gap detected → halt delivery; route to clearance work.
- Cue sheet pending PRO administrator → flag and follow up.
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.
- 9d ago First seen · 104 lines · 43 tokens per session scan A 64331033ed0b
sound-sync-rights-pack is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 1,741 once invoked, about $0.0002 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.
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.
finalize
A final submission workflow that protects a client's edits, creates a signed PDF, and prepares a filing package for the 02hearings location.