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-set-design)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/sound-performance-set-design"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sound-performance-set-design/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-set-design"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sound-performance-set-design.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 | $0.00057 | $0.00764 |
| Opus 5 | $0.00028 | $0.00382 |
| Sonnet 5 | $0.00011 | $0.00153 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
sound-performance-set-design 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 6d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sound-performance-set-design
Load verticals/sound-intelligence/SKILL.md, agents/starlight-sound-performance.md, skills/sound-intelligence/performance-design.md. Produce a Set Design.
Disclaimer
Live performance touches hearing-health risk and broadcast-rights territory. Not legal/medical advice.
Process
- Disclaim.
- Length-aware design (different architectures per length).
- Opener / peak / closer logic. Peak typically 60-70% through; not at the end (peak-end memory bias).
- Tension-and-release across set (extending Huron from song to set-level).
- Instrumentation logistics sequenced.
- Transition design per song-to-song boundary.
- Compose with Composition's arrangement (set-flexible vs. set-fixed tags).
- Save:
sound-intelligence/performance/set-<show-slug>-<YYYY-MM-DD>.md.
Output format
# Set Design — <Show> — <YYYY-MM-DD>
## Context
- Length: <minutes>
- Venue type: <listening-room/festival/dance-floor/seated-theater>
- Date: <date>
## Setlist (in order)
| # | Song | Length | Energy level | Instrumentation | Transition to next |
|---|---|---|---|---|---|
| 1 | <opener> | 4:00 | medium-up | <list> | <move> |
| 2 | ... | 5:00 | up | ... | <move> |
| 3 | ... | 4:30 | peak | ... | <move> ← peak around here for some sets |
| ... | ... | ... | ... | ... | ... |
## Tension-and-release arc
<Verbal map: opener establishes / first peak at song N / valley at song M / second peak / closer resolves>
## Opener logic
<Why this opener — what does the room need to hear first?>
## Peak logic
<Where is the peak (typically 60-70% through)? Why this song? What does it do?>
## Closer logic
<Why this closer? What's the resolution?>
## Instrumentation logistics
- Setup transitions: <where instrument changes happen; gear required>
- Breaks: <if any; where; why>
## Set-flexibility
- Set-flexible (can be reordered): <list>
- Set-fixed (sequence depends on tension-and-release positioning): <list>
**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.
- 6d ago First seen · 80 lines · 57 tokens per session scan A 34b50bfffcf3
sound-performance-set-design is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 764 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.