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/welcome)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/welcome"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/welcome.svg" alt="Measured on agentmods" 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 | $0.00042 | $0.01229 |
| Opus 5 | $0.00021 | $0.00615 |
| Sonnet 5 | $0.00008 | $0.00246 |
| Haiku 4.5 | $0.00004 | $0.00123 |
Grade A, and why
welcome 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 4d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/welcome
Load ONBOARDING.md and DELIVERY.md if present — both arrive in this release. If either is missing, proceed with the content inline and emit a one-line notice: <filename> not yet loaded — using inline defaults. Also load SIP.md and VERTICALS.md. This command orients. It does not commit. /intake commits.
Input
$ARGUMENTS
Process
-
Detect or ask for track. If
$ARGUMENTSisbuilderorcreator, use it. Otherwise ask one question: Are you here to build in a terminal, or to create from your voice? Wait for the answer. Do not infer. -
Show the four routes, tailored to track.
- Builder track receives terminal commands beside each route (
/alliance-forge,/vertical-spawn, substrate contribution via/luminor-boardthen/sip-attest, sovereign spawn via/sovereign-spawnwith sovereign-tier scaffolding). - Creator track receives conversational paths. The terminal command is named, but framed as what your implementer runs on your behalf. Concierge handoff is explicit.
- Builder track receives terminal commands beside each route (
-
Show the delivery menu. Six deliverables from
DELIVERY.md, one line each. IfDELIVERY.mdis not yet present, use this inline default:- Substrate adoption — your repo, SIP-compliant,
/sip-attestready. - Alliance forge — 2–5 sovereign nodes, scoped protocol, first cycle scheduled.
- Vertical spawn — one domain, one system, first artifact target named.
- Sovereign spawn — full fork pattern, your own command namespace.
- Concierge session — 60-minute orientation, voice-led, artifact-closed.
- Luminor Board pressure-test — one proposal, five vectors, synthesis + recommendation.
- Substrate adoption — your repo, SIP-compliant,
-
Show the sovereignty clause in plain language. Use this exact framing, every time: You stay sovereign in your domain. Starlight does not own your work. The substrate is MIT, the canon licensed separately, attribution via "Built on SIP" is the sole compounding mechanism. Advice never overrides.
-
Point to
/intakeas the single next step. One arrow. No menu sprawl. If amemory/welcome-log/entry exists for this session (same agent, same day), skip re-orientation and point directly to/intakewith a one-line recap.
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.
- 4d ago First seen · 90 lines · 42 tokens per session scan A 28042f8654a5
welcome is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 1,229 once invoked, about $0.0002 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
agent
Create and manage custom AI agents.
memories
View and manage learned memories.
mpm-session-resume
Load context from paused session.
forget
Delete specific memories.
learn
Add new learning to memory.
learn
End-of-session learning loop — analyze signals, approve instincts, capture directives, refresh MEMORY.md. Invokes dreamteam learn; one source of behavioral truth shared with the team.md SESSION LEARNING step.