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-placement-thesis)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/sound-sync-placement-thesis"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sound-sync-placement-thesis/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-placement-thesis"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sound-sync-placement-thesis.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 | $0.00061 | $0.01353 |
| Opus 5 | $0.00030 | $0.00677 |
| Sonnet 5 | $0.00012 | $0.00271 |
| Haiku 4.5 | $0.00006 | $0.00135 |
Grade A, and why
sound-sync-placement-thesis 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 7d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sound-sync-placement-thesis
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, the brief-fit verdict (sound-intelligence/sync/brief-fit-<brief-slug>-*.md — REQUIRED, halt if missing), catalog state files, and Genius Profile for supervisor-facing voice. Produce a Placement Thesis — the pitch document. Hand off to license-economics or rights-pack.
Disclaimer (non-waivable)
Placement decisions touch rights law and brand-association. This is system architecture, not legal advice. Every specific placement requires sign-off from the practitioner's qualified music counsel.
Input
$ARGUMENTS
Process
- Disclaim. Non-waivable opener.
- Verify upstream. Brief-fit verdict must exist with PROCEED outcome. If missing or REFUSE — halt. The placement thesis presumes the gate has passed.
- Select 3-7 candidate tracks. From the brief-fit's catalog match, narrow to the 3-7 strongest fits. Fewer than 3 = pitch is thin (re-evaluate brief-fit). More than 7 = pitch dilution (volume thinking).
- Per-track structure. ISRC reference; version (main / instrumental / sync-grade-dynamic-range alternate-master); reference cues from the brief that this track matches (mood / tempo / instrumentation / emotional arc); clearance flags (samples, AI involvement, contributor-split status from brief-fit Axis 3).
- Match-rationale per track. One paragraph per track in supervisor-facing voice (warm, business-precise, refuses both casual rights language and over-eager pitch language). The rationale names exactly which brief cue the track addresses; specificity predicts placement.
- Strongest-first ordering. Top track = strongest fit; ordering matters because supervisors read the first 1-2 with attention and skim the rest.
- Alternative-version flag per track. Where instrumental / radio-edit / sync-grade-master exists, flag explicitly so the supervisor knows what's available without asking.
- Catalog-context offer. Brief paragraph (≤3 sentences) offering related catalog the supervisor might consider for adjacent scenes / future briefs. Light touch — refuses upsell-aggression.
- Practitioner-bio paragraph (one paragraph max). In Genius voice; names the catalog scope and the sync-relevant credits without resume-bloat.
- Save. Write to
sound-intelligence/sync/placement-thesis-<brief-slug>-<YYYY-MM-DD>.md. - Hand off. Name exactly one next move:
- Pitch sent → wait for supervisor response.
- Supervisor expresses interest →
/sound-sync-license-economicsfor the deal-shape work. - Brief-fit needs revision → return to
/sound-sync-brief-fit.
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.
- 7d ago First seen · 95 lines · 61 tokens per session scan A 0fd0fa08075a
sound-sync-placement-thesis is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 1,353 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.
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.