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.
npx agentmods add commands/frankxai/starlight-intelligence-system/intakegit 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/intake)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/intake"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/intake.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 | $0.01628 |
| Opus 5 | $0.00021 | $0.00814 |
| Sonnet 5 | $0.00008 | $0.00326 |
| Haiku 4.5 | $0.00004 | $0.00163 |
Grade A, and why
intake 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 5d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/intake
Load SIP.md, VERTICALS.md, ALLIANCE.md (if present), VOICES.md. Also load agents/starlight-concierge.md — if the file is not yet present in this release, proceed with Navigator + Orchestrator voice and emit a one-line notice: concierge agent not yet loaded — proceeding with Navigator + Orchestrator. Triage the inbound. Route to exactly one next command, or halt with a readiness gap named.
Input
$ARGUMENTS
Process
-
Scan for readiness signals. An inbound is ready when all four are present:
- Named problem. A concrete target, not a mood. "I want to compose my catalog" is a mood. "My 140-song Suno catalog has no search layer and I lose ideas" is a problem.
- Preferred format. Essay, repo, session, artifact. If unstated, infer from the inbound shape and name the inference.
- Time horizon. A week, a cycle, a quarter. "Someday" is not a horizon.
- Sovereignty. They own the domain they are describing — not asking Frank to own it for them.
If any signal is missing, emit at most 3 clarifying questions, one per missing signal, and halt. Do not route an unready inbound. Log the halt to
memory/intake/with reason. -
Classify the route. Apply in order; first match wins.
- Route A — Substrate contribution. The inbound proposes changing SIP itself — a new layer, a changed attestation format, a protocol invariant. High bar. Routes to
/luminor-board, then (if REVISE or PROCEED) to/sip-atteston the proposed change set. - Route B — Alliance forge. The inbound is about composing intelligence systems across parties and the newcomer can name ≥2 sovereign collaborators with non-overlapping domains. Routes to
/alliance-forge. - Route C — Vertical spawn. The inbound is about one domain the newcomer owns and wants a system for — creator catalog, wealth thesis engine, personal OS, creative world, research stack. Routes to
/vertical-spawn. - Route D — Sovereign spawn. The inbound is about forking the whole substrate pattern to run their own ecosystem under their own name. Routes to
/sovereign-spawnwith sovereign-tier scaffolding and a/<name>-*command namespace. - No clean fit. Emit ONE clarifying question that forces a route. Re-classify. Do not route on ambiguity.
- Route A — Substrate contribution. The inbound proposes changing SIP itself — a new layer, a changed attestation format, a protocol invariant. High bar. Routes to
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.
- 5d ago First seen · 99 lines · 42 tokens per session scan A 9671825804da
intake 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 1,628 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 2026-08-31.
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.