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/sovereign-spawn)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/sovereign-spawn"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sovereign-spawn/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/sovereign-spawn"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sovereign-spawn.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 | $0.00054 | $0.02163 |
| Opus 5.5 | $0.00022 | $0.00865 |
| Sonnet 5.5 | $0.00011 | $0.00433 |
| Haiku 4.5 | $0.00005 | $0.00216 |
Grade A, and why
sovereign-spawn 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sovereign-spawn
Load SIP.md, SIS.md, VOICES.md, STACK.md, VERTICALS.md. Spawn a full sovereign intelligence system under SIP — not a vertical (one domain) and not an alliance (multi-party). A full substrate-aware fork the sovereign owns, operates, and extends.
Input
$ARGUMENTS
When this command fires
/intakeclassified inbound as Route D (sovereign spawn).- Sovereign wants to run the whole SIS pattern — substrate awareness + their own operational layer — not just one vertical under someone else's substrate.
- Sovereign accepts the sovereignty clause (SIP § 5) and will ship attestation on their own artifacts.
When this command does NOT fire
- Single-domain builder →
/vertical-spawn(cheaper, same substrate, no full fork). - 2+ parties composing →
/alliance-forge(shared not forked). - Substrate change proposal →
/luminor-board→ possibly contribute back to SIP itself.
Process
-
Validate the five spawn conditions:
- Sovereignty clear. Sovereign names their declared domain, their entity (person / company / DAO), and the public surface they'll operate. Ambiguity → halt, name the structural fork.
- Substrate awareness real. Sovereign has read SIP.md. Ask one comprehension question about Layer 5 (sovereignty clause) before proceeding. Incorrect answer → require re-read, do not soften.
- Attestation committed. Sovereign agrees every cross-party artifact they ship carries "Built on SIP". Silent composition is a breach.
- Name not already registered. Check
VERTICALS.mdandREGISTRY.md. Collision → halt, require rename. - Fork intent honest. Sovereign can name one artifact they'll ship in the first 30 days that the fork enables and their prior stack did not. No answer = not ready to spawn; route to Concierge for re-qualification.
-
Build the sovereign's SIS scaffold structure:
<sovereign-name>/
├── README.md — what this sovereign system is, domain, public URL
├── SIP.md — symlink or upstream reference to starlightintelligence.org/protocol
├── SIS-instance.md — this fork's substrate map (what operational layer runs on top)
├── SKILL.md — sovereign behavior definition (what AI adopts at this layer)
├── AGENTS.md — sovereign's named agents (may inherit 5 archetypes or declare new)
├── MEMORY.md — instance state (public template — private state stays private)
├── SOUL.md — sovereign essence (the thing that must not drift)
├── CANON.md — optional; if not adopting canon, declare decline explicitly
├── STACK.md — inherited from Starlight STACK.md or overridden
├── VOICES.md — inherited or extended per SIP § Layer 6
├── REGISTRY.md — sovereign's MCP server registry
├── ATTESTATIONS.md — append-only ledger for their /sip-attest emissions
├── .claude/commands/
│ ├── sip-attest.md — mirrored from substrate
│ ├── vertical-spawn.md — mirrored (sovereign can spawn their own verticals)
│ ├── alliance-forge.md — mirrored (sovereign can forge alliances under SIP)
│ ├── luminor-board.md — mirrored
│ ├── <sovereign-slug>-*.md — sovereign-tier commands they author
├── agents/ — sovereign's operational agents (can mirror SIS 7 or declare new)
├── memory/ — sovereign vault directory (6 vaults or their own taxonomy)
└── private/ — gitignored; instance state stays here
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 · 151 lines · 54 tokens per session scan A ff9b0a274630
sovereign-spawn is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (11 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 2,163 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.
agent-list
List all available agents with their capabilities (MPM-provided — may be shadowed by a user /agent-list command).