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-vocal-chain)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/sound-production-vocal-chain"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sound-production-vocal-chain/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-vocal-chain"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sound-production-vocal-chain.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 | $0.00055 | $0.01014 |
| Opus 5.5 | $0.00022 | $0.00406 |
| Sonnet 5.5 | $0.00011 | $0.00203 |
| Haiku 4.5 | $0.00006 | $0.00101 |
Grade A, and why
sound-production-vocal-chain 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sound-production-vocal-chain
Load verticals/sound-intelligence/SKILL.md, agents/starlight-sound-production.md, skills/sound-intelligence/production-systems.md. Produce a Vocal Chain matched to THIS voice, THIS song.
Disclaimer (non-waivable)
Vocal-chain decisions touch AI-vocal licensing if any AI is involved. AI-vocal-impersonation without written license is non-shippable.
Input
$ARGUMENTS
Process
- Disclaim.
- Voice character. Brief: timbre, range, dynamic profile, sibilance frequency, breath/articulation pattern. Vocal chain serves THIS voice.
- AI-vocal status. None / disclosed / refused-as-impersonation. Refused = halt.
- Tuning posture. Untuned / lightly-tuned / heavily-tuned-as-effect.
- De-essing. Frequency-targeted to this voice's sibilance band.
- EQ. Subtractive-first (cut 250-400 Hz mud) before adding presence.
- Compression. Attack and release matched to phrasing.
- Saturation. Harmonic excitement at perceived-volume cost.
- Sends. Parallel reverb / vocal-doubler / delay-for-emphasis. Discrete sends.
- Automation map. When the vocal lifts, what plugins respond.
- Save.
sound-intelligence/production/vocal-chain-<slug>-<YYYY-MM-DD>.md.
Output format
# Vocal Chain — <Voice / Song> — <YYYY-MM-DD>
> **AI-vocal-impersonation without written license is non-shippable.**
## Voice character
- Timbre / range / dynamic profile / sibilance frequency / breath pattern: <description>
- AI involvement: <none | disclosed | refused-as-impersonation>
## Chain (in order)
1. **Tuning** — <untuned | lightly-tuned at <window> | heavily-tuned as effect>
2. **De-essing** — <frequency target; ratio; threshold>
3. **EQ (subtractive)** — <cuts: e.g., -3 dB at 280 Hz Q=2; pull mud>
4. **EQ (additive)** — <boosts: e.g., +1.5 dB at 4 kHz wide; presence>
5. **Compression** — <ratio / attack / release / threshold; matched to phrasing>
6. **Saturation** — <plugin / drive / mix>
7. **EQ (post-comp)** — <if needed>
8. **Sends:**
- Reverb send: <plate / hall / spring; pre-fader; ratio>
- Doubler send: <if used>
- Delay send: <quarter / dotted-eighth; feedback; mix>
## Automation map
- V1: <chain settings>
- Pre-chorus: <changes>
- Chorus: <changes — likely more compression, more send, more presence>
- Bridge: <changes — often less, more space>
- Final chorus: <changes — peak>
## Refusal-check
- Default-chain deployment: refused
- AI-vocal-impersonation: refused unless written license
- Auto-tune as repair (not as artistic effect): refused as default
## Load-bearing next move
Tracking session with this chain printed and reference-monitored.
---
**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 · 98 lines · 55 tokens per session scan A b553586312c3
sound-production-vocal-chain is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (11 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 1,014 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.