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-performance-live-mix)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/sound-performance-live-mix"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sound-performance-live-mix/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-performance-live-mix"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sound-performance-live-mix.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 | $0.00058 | $0.00908 |
| Opus 5 | $0.00029 | $0.00454 |
| Sonnet 5 | $0.00012 | $0.00182 |
| Haiku 4.5 | $0.00006 | $0.00091 |
Grade A, and why
sound-performance-live-mix 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sound-performance-live-mix
Load verticals/sound-intelligence/SKILL.md, agents/starlight-sound-performance.md, skills/sound-intelligence/performance-design.md. Produce a Live Mix Plan.
Disclaimer
Hearing-health protection requires audiologist consultation. Live-sound exposure typically exceeds NIOSH limits without protection. Not medical advice.
Process
- Disclaim.
- FOH priorities (vocal first / rhythm second / harmonic instruments / texture).
- Per-performer monitor mix designed.
- IEM vs. wedge decision with hearing-health rationale.
- Redundancy plan per critical path (backup transmitter / mic / playback / console-mode).
- Soundcheck protocol matched to room and budgeted soundcheck time.
- Hearing-health baseline addressed.
- Save:
sound-intelligence/performance/live-mix-<show-slug>-<YYYY-MM-DD>.md.
Output format
# Live Mix Plan — <Show> — <YYYY-MM-DD>
> **Hearing-health protection requires audiologist consultation. Not medical advice.**
## Console + monitor architecture
- Console: <digital model / analog model>
- Monitor type: <IEM / wedge / hybrid>
- Hearing-health rationale: <why this choice>
## FOH priorities (general; song-specific overrides noted)
1. Lead vocal
2. Rhythm section (drums + bass)
3. Harmonic instruments
4. Texture
5. <Song-specific override examples>
## Per-performer monitor mix
| Performer | Heavy on | Light on | Talkback enabled? |
|---|---|---|---|
| Lead vocal | own vocal + click | drums (light) | yes |
| Drums | click + bass + own kit | vocals (light) | yes |
| ... | ... | ... | ... |
## Redundancy plan (per critical path)
| Critical path | Primary | Backup | Failover protocol |
|---|---|---|---|
| Lead vocal mic | <mic> | <backup mic on stand> | swap; sound engineer flips channel |
| Wireless transmitter | <pack> | <backup pack at FOH> | swap |
| Playback rig | <laptop + interface> | <secondary laptop with same session> | failover via switch |
| Digital console | <model> | <manual mode + analog backup if applicable> | engineer pulls preset |
## Soundcheck protocol
- Time budget: <minutes>
- What's checked: <list — line check, monitor check, full-band check, vocal-effects check>
- What's checked-against-recorded-reference: <studio-master comparison via wedge / FOH>
- What's left to ear-and-feel-but-not-skipped: <list>
## Hearing-health baseline
- IEM volume calibrated to: <SPL target>
- Ambient mix preserved: <yes / no>
- Performer hearing-test cadence: <annual / pre-tour / post-tour>
- FOH SPL limits: <NIOSH-aware; specific dB limit per venue capacity>
## Refusal-check
- Single-point-of-failure: refused
- Soundcheck skipped: refused
- "Loud-as-feel" default: refused
**Built on SIP** — SIP v1.1.0 · Sound Intelligence — Performance · 2026-04-26
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 · 92 lines · 58 tokens per session scan A d53960569911
sound-performance-live-mix is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 908 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.