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-brief-fit)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/sound-sync-brief-fit"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sound-sync-brief-fit/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-brief-fit"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sound-sync-brief-fit.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 | $0.00051 | $0.01652 |
| Opus 5 | $0.00026 | $0.00826 |
| Sonnet 5 | $0.00010 | $0.00330 |
| Haiku 4.5 | $0.00005 | $0.00165 |
Grade A, and why
sound-sync-brief-fit 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sound-sync-brief-fit
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 catalog state files at sound-intelligence/catalog/<release-state-files> if present in the practitioner's runtime vault (this path is instance-state, not substrate-shipped), and active vision boundaries from MEMORY.md. Produce a Brief-Fit Verdict — pass to placement thesis OR refuse with documented rationale. Hand off to exactly one next command.
Disclaimer (non-waivable)
Sync placement decisions touch rights law, contributor splits, sample clearances, AI involvement disclosure, and brand-association liability. This is system architecture, not legal advice. Every specific placement requires sign-off from the practitioner's qualified music counsel. Vision-boundary refusal is non-waivable; the boundary either holds or gets revised at MEMORY.md level deliberately, never "this once" under deal pressure.
Input
$ARGUMENTS
Process
- Disclaim. Non-waivable opener.
- Read brief. Brief content, source (library / direct-supervisor / brand / agency), budget range if disclosed, timeline, content context (film / TV / commercial / trailer / branded content / political / video game / etc.), exclusivity request.
- Axis 1 — Catalog match. Does the practitioner have tracks that fit the brief? Search catalog by mood / tempo / instrumentation / lyric-or-instrumental / emotional arc against brief requirements. Three or more matching candidates → pass. Two matches → conditional pass (named gap). Zero or one match → refuse-on-catalog OR route to Composition for purpose-built work (rare; only when budget justifies).
- Axis 2 — Master availability. For each candidate track: does the master state allow placement? Rights structure permits sync (no exclusivity-elsewhere conflict)? Sync-availability flag true in metadata? Alternate-master available if brief specifies (sync-grade-dynamic-range master vs. streaming master)?
- Axis 3 — Rights structure. Per candidate: splits documented; sample clearances complete; AI involvement disclosed (per
/sip-attest-audiodoctrine); contributor consents on file. Any incomplete clearance → flag and refuse on this axis until resolved. - Axis 4 — Vision-boundary respect. Pull active vision boundaries from MEMORY.md. Common: refuses-political-campaign-sync, refuses-violence-soundtrack, refuses-extractive-fossil-fuel-brand, refuses-AI-vocal-impersonation-license-out, refuses-children's-content-without-curated-fit. Per-practitioner the list varies. Compare brief to each active boundary. Any contradiction → non-waivable refuse. The deal pressure does not override; if the boundary is to be revised, that revision happens at MEMORY.md, deliberately, not "this once."
- Verdict synthesis.
- All four axes pass → PROCEED to
/sound-sync-placement-thesis. - Catalog or master axis fails → REFUSE-ON-AXIS, document, no further sync work for this brief.
- Rights-structure axis fails → REFUSE-PENDING-CLEARANCE, document gaps, route to clearance work before re-running.
- Vision-boundary axis fails → REFUSE-ON-BOUNDARY, document, communicate the refusal honestly to brief source if relationship warrants.
- All four axes pass → PROCEED to
- Document refusal. Refusals are first-class artifacts. The refusal-on-boundary letter (when relationship warrants) is in practitioner's voice via Genius — direct, warm, non-apologetic, non-compromising.
- Save. Write to
sound-intelligence/sync/brief-fit-<brief-slug>-<YYYY-MM-DD>.md. - Hand off. Name exactly one next move:
- PROCEED →
/sound-sync-placement-thesis. - REFUSE-ON-CLEARANCE → clearance work (sample clearance, contributor-split documentation, AI disclosure).
- REFUSE-ON-BOUNDARY → refusal letter (if relationship warrants); MEMORY.md boundary update if practitioner wants to deliberately revise (rare).
- PROCEED →
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 · 103 lines · 51 tokens per session scan A cfeaaf900adf
sound-sync-brief-fit is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 1,652 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.