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-production-mix-plan)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/sound-production-mix-plan"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sound-production-mix-plan/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-production-mix-plan"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sound-production-mix-plan.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 | $0.00062 | $0.01376 |
| Opus 5.5 | $0.00025 | $0.00550 |
| Sonnet 5.5 | $0.00012 | $0.00275 |
| Haiku 4.5 | $0.00006 | $0.00138 |
Grade A, and why
sound-production-mix-plan 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 1mo 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sound-production-mix-plan
Load verticals/sound-intelligence/SKILL.md, agents/starlight-sound-production.md, skills/sound-intelligence/production-systems.md, and song's Arrangement + Catalog clearance status. Produce a Mix Plan.
Disclaimer (non-waivable)
Mix decisions involving samples or AI vocals touch rights. This is system architecture, not legal advice.
Input
$ARGUMENTS
Process
- Disclaim.
- Rights-and-clearance gate. Pull sample clearance + AI-vocal-license status from Catalog. Any uncleared exposure halts the mix plan.
- Frequency budget. Allocate spectrum: sub / low-mids / mids / high-mids / air. What lives where? What's masking what?
- Gain-stage hierarchy. Channels -6 / Buses -10 / Master -3 pre-limiter.
- Dynamic-range envelope. Per song: where it breathes, where it lifts, where master limiter works and where it stays out.
- Bus structure. Drums bus / vocals bus / instrument groups / parallel-compression bus / master bus.
- Reference tracks. 2-3 chosen for what they prove (translation, dynamic feel, vocal-clarity reference) — not for genre similarity alone.
- Sync-vs-streaming dual-master plan. If sync-availability flag is true → plan sync-grade alternate-master alongside streaming master.
- Save.
sound-intelligence/production/mix-plan-<song-slug>-<YYYY-MM-DD>.md. - Hand off. Patching session (not a command). Then
/sound-production-master-plan.
Output format
# Mix Plan — <Song Title> — <YYYY-MM-DD>
> **Mix decisions involving samples or AI vocals touch rights. This is system architecture, not legal advice.**
## Context
- Arrangement: <path>
- Sample clearance status: <all-cleared | pending: <list> — mix-final blocked>
- AI-vocal-license status: <not-applicable | disclosed-in-metadata | pending>
## Frequency budget
| Band | Hz range | Primary elements |
|---|---|---|
| Sub | 20-80 | <kick, bass — mono ≤100 Hz> |
| Low-mids | 80-300 | <list> |
| Mids | 300-2k | <vocal core, lead instruments> |
| High-mids | 2k-8k | <vocal presence, cymbals> |
| Air | 8k+ | <shimmer, reverb tails> |
**Masking hotspots identified:** <list with resolution plan — sidechain / EQ-carve / arrangement-level fix>
## Gain-stage hierarchy
- Channels peaks at: **-6 dBFS**
- Buses at: **-10 dBFS**
- Master pre-limiter at: **≤-3 dBFS**
## Dynamic-range envelope
| Section | Density | Master limiter activity | Notes |
|---|---|---|---|
| V1 | low | none | breathes |
| Pre | med | minimal | starts loading |
| Chorus | peak | working ~2-3 dB | lift |
| ... | ... | ... | ... |
PSR target: **≥ 6 dB** (ideally ≥ 8 dB).
## Bus structure
- Drums bus → master
- Vocals bus → master
- Instrument groups → instrument-bus → master
- Parallel compression bus (drums or vocals) → master
- Master bus → limiter → output
## Reference tracks
1. <Track 1 — what it proves>
2. <Track 2 — what it proves>
3. <Track 3 — what it proves>
## Sync-vs-streaming dual-master plan
- **Streaming master target:** Spotify ~-14 LUFS / Apple ~-16 LUFS (verify spec at master time); PSR ≥ 6 dB; true-peak -1.0 dBTP
- **Sync-grade alternate-master:** PSR ≥ 12 dB; K-12 reference; target-loudness lower; true-peak -2.0 dBTP for safety
- **If sync-availability flag is FALSE:** streaming master only
## Refusal-check
- "Fix it in the mix" for arrangement-failures: refused
- Loudness-war target: refused
- Single-master-for-all-destinations: refused (when sync flag is true)
## Load-bearing next move
**Patching session.** Then `/sound-production-master-plan <song-slug>`.
---
**Built on SIP** — Starlight Intelligence Protocol
- Substrate: starlightintelligence.org/protocol v1.1.0
- Layers used: [file-contract, attestation, commands, sovereignty]
- Verticals: [email protected] (Sound Intelligence reference vertical — Production sub-system)
- Generated: <ISO date>
---
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.
- 1mo ago First seen · 129 lines · 62 tokens per session scan A 452ce16e3fbf
sound-production-mix-plan is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (11 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 1,376 once invoked, about $0.0002 per session on Opus 5.5. 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.