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/model-revenue)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/model-revenue"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/model-revenue/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/model-revenue"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/model-revenue.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 | $0.00056 | $0.02843 |
| Opus 5 | $0.00028 | $0.01422 |
| Sonnet 5 | $0.00011 | $0.00569 |
| Haiku 4.5 | $0.00006 | $0.00284 |
Grade A, and why
model-revenue 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 10d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/model-revenue
Load SIP.md, VOICES.md, agents/starlight-business.md, skills/business/revenue-modeling.md, and if present the person's Genius Profile (genius/profile-<slug>.md) and Freedom Path (genius/freedom-path-<slug>.md). Produce a Revenue Model. Hand off to exactly one next command.
Disclaimer (non-waivable)
This is thinking architecture, not tax/legal/financial advice. Real decisions require a qualified professional in your jurisdiction.
This command organizes your revenue thinking. It maps what exists, reveals what is capped by your time vs. what compounds, flags concentration risk, sets margin floors. It does not prescribe what to sell, price, or cut. You make those calls; the map makes them legible.
Input
$ARGUMENTS
Process
-
Disclaim. Open every output with the non-waivable disclaimer.
-
Load context. Read Genius Profile + Freedom Path if present. Revenue streams will be mapped to KEEP/DELEGATE/AUTOMATE/KILL buckets using the Profile's taxonomy. If no Profile exists, flag it in the output and note that excavation-first typically produces sharper revenue design — but proceed if the person has provided enough revenue data.
-
Current revenue audit. For each active stream, collect:
- Stream name (internal label)
- Customer count (last 12 months)
- Gross revenue (last 12 months)
- Delivery time (hours/month spent)
- Bucket alignment (KEEP/DELEGATE/AUTOMATE/KILL) if Profile exists
- Primary + secondary revenue archetype (from library: product, service, subscription, license, royalty, advisory, affiliate, sponsorship, community, productized consulting, group program, book/evergreen)
If the person cannot provide enough data, halt and request the missing data. Never model forward from an unmapped present.
-
Unit economics per stream. For each stream, surface:
- Unit of sale, unit price, unit cost to deliver, unit gross margin, time per unit
-
Margin analysis. Compare each stream's gross margin to its floor (knowledge products ≥60%, service ≥40%, subscription/membership ≥50%, etc.). Flag any stream below its floor.
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.
- 10d ago First seen · 207 lines · 56 tokens per session scan A 17ef8059837c
model-revenue is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 2,843 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 2026-08-31.
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.
performance
Generate a strategy performance report with key metrics.