Borrowing it
Nothing to install: this file belongs to frankxai/Starlight-Intelligence-System. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/frankxai/Starlight-Intelligence-System/main/.claude/commands/estate-provision.mdgit 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/estate-provision)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/estate-provision"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/estate-provision/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/estate-provision"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/estate-provision.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 | $0.00049 | $0.01421 |
| Opus 5 | $0.00024 | $0.00711 |
| Sonnet 5 | $0.00010 | $0.00284 |
| Haiku 4.5 | $0.00005 | $0.00142 |
Grade A, and why
estate-provision 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/estate-provision
Load templates/estate-os/README.md, AGENTS.md, SKILL.md, MEMORY.md, SOUL.md (this estate's overrides if present), the client's 4-layer Blueprint (from /estate-blueprint or prior), and relevant substrate canon (STACK.md, ORCHESTRATION_ENGINE.md, claws/, /si command, SIP §5).
One sentence on what this command produces: A fully scaffolded sovereign directory (or in-place composition) using the thin starlight-estate-os profile as the reusable 80%, the client's Genius-grounded 4-layer config applied as the tuned 20%, an initial build brief with /si-dispatched first-wave tasks for Mind/Mesh components, and all artifacts carrying real SIP attestation + promotion commitments.
Input
$ARGUMENTS
Process
-
Scaffold from profile — Create or reference the estate root using the starlight-estate-os composition rules (file contract, inherited 10-IS + Orchestrator, production Mesh primitives from ORCHESTRATION_ENGINE + /si + claws + Memory Bus, module scaffolds from vertical/domain starters). Wire private/ (gitignored), ATTESTATIONS.md, and cycle-0 MEMORY.md. Never copy the entire substrate; compose by reference + thin overrides.
-
Apply 4-layer Blueprint —
- Persona / Naming skin (plain/pantheon/luminor/chess/custom; voice mappings from VOICES.md + client's Genius).
- Topology / Swarm shape (council, yolo/hive conductor, amplification Claws mesh, Hermes retrieval, hybrid — drawn from ORCHESTRATION_ENGINE 6 patterns + swarm consensus).
- Kernel / insight density (standard agents for volume; selective advanced/Luminor-grade only where blueprint justifies cost; flag for routing).
- Modules (base 10-IS + specific domain sub-stacks via /spawn-domain-stack patterns; register in VERTICALS.md or client registry). Ground every layer in the excavated Genius Profile + Freedom Path KEEP items. Produce the tuned AGENTS.md overrides, SKILL.md invariants, SOUL.md (if not already), and estate-specific .claude/commands/ stubs.
-
Initial build brief & dispatch via /si — Emit a concise, actionable Build Brief (30/90-day targets, first Pilot workflows, key harness configs, claw bootstrap sequence, vault seeding plan, attestation schedule). Then intelligently dispatch the first construction wave:
- Architecture / topology lock → Claude (or primary substrate lane) via /si.
- Implementation of core agents/skills/commands/harnesses → Codex or targeted lane.
- Research / long-context / browser swarm components → Gemini or Antigravity via /si.
- Always preserve context with handoff packets per cli-tool-router. Leave receipts in operational-vault and estate logs. Use progressive loading and token budgets from the Orchestration Engine. Route high-stakes (substrate touch, encoded-self, public) through /starlight-board pre-pass.
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 · 83 lines · 49 tokens per session scan A 2effd0b1e8de
estate-provision is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 1,421 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.