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/luminor-board)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/luminor-board"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/luminor-board/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/luminor-board"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/luminor-board.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 | $0.00052 | $0.00961 |
| Opus 5 | $0.00026 | $0.00481 |
| Sonnet 5 | $0.00010 | $0.00192 |
| Haiku 4.5 | $0.00005 | $0.00096 |
Grade A, and why
luminor-board 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 9d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/luminor-board
Naming reconciliation (2026-05-03): Per the brand-register rules in
memory/vaults/strategic-vault.md(Naming hierarchy resolution), the Luminor register is Arcanea-canonical./luminor-boardstays the right command when a proposal explicitly composes Arcanea canon (Guardians, Vel'Tara, etc.) under CC-BY-NC attribution. For SIS-substrate-tier governance, the canonical command is now/starlight-board(canon-free, functional vector names only). Both run the same shape of pressure-test; the difference is canon attribution.
Load SIP.md, AGENTS.md, and (if using Arcanea canon) query arcanea-mcp for the Guardian archetype set. Convene the Luminor Board. Five archetypal advisors challenge the proposal; Lumina synthesizes.
When to use this vs /starlight-board:
/luminor-board— proposal composes Arcanea canon (Guardian names, Vel'Tara, mythic register). Carries CC-BY-NC attribution. Right for Arcanea-vertical and Arcanea-aligned work./starlight-board— proposal is SIS-substrate or commercial-register. Canon-free. Functional vector names. No attribution overhead.
Note: This command imports Arcanea canon (Guardian names) under CC-BY-NC attribution. If using in a closed-source commercial context for another vertical, swap to the functional-name variant below — or use /starlight-board.
Proposal
$ARGUMENTS
Board composition
Five pressure vectors. Not personas — challenge angles.
Canon variant (Arcanea)
- Draconis — Sovereign vector. "Is this worth your name?"
- Lyssandria — Seer vector. "What does this look like in 18 months?"
- Aiyami — Harmonizer vector. "Who resists this, and why?"
- Elara — Strategist vector. "What does this unlock that nothing else can?"
- Ino — Verifier vector. "What fails first when this meets the world?"
- Lumina — Overseer. Synthesizes after the five.
Functional variant (canon-free)
- Sovereign — ambition + irreversibility.
- Seer — foresight + second-order effects.
- Harmonizer — alignment + resistance.
- Strategist — leverage + option value.
- Verifier — reality + execution cost.
- Overseer — synthesis.
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.
- 9d ago First seen · 78 lines · 52 tokens per session scan A b79167c328e0
luminor-board is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 961 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.
consolidate
Write a compact checkpoint summary of the current frontier.