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/estate-blueprint)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/estate-blueprint"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/estate-blueprint/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-blueprint"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/estate-blueprint.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 | $0.00092 | $0.01979 |
| Opus 5 | $0.00046 | $0.00989 |
| Sonnet 5 | $0.00018 | $0.00396 |
| Haiku 4.5 | $0.00009 | $0.00198 |
Grade A, and why
estate-blueprint 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 12d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/estate-blueprint
Load SIP.md, STACK.md, docs/ARCHITECTURE.md, VOICES.md, NAMING.md, docs/strategic/sip-web4-substrate-strategy.md, docs/delivery/estate-army-commissioning-workflow.md, the client's Genius Profile + Freedom Path (required for high-fidelity) and Vision if available. Produce the locked 4-layer configuration for the estate (Mind + Mesh + Steward).
This is the "thin tuned layer" generator. It turns scattered client inputs into the precise blueprint that drives scaffold, build, and Steward phases. Per board verdict, this is internal/R&D until R3 closed (2026-06-18 deadline); do not expose to clients or use in SOWs before then.
Input
$ARGUMENTS
Prerequisites (halt if missing)
- Named person or alliance (the sovereign owner).
- One-line domain or vision anchor.
- Genius Profile (at minimum the synthesis edge + repeated frameworks + KEEP bucket items). If absent: recommend
/discover-geniusfirst. - Freedom Path (KEEP/DELEGATE/AUTOMATE/KILL) — this directly seeds the delegation surface of the army.
- (Optional but strongly recommended) Vision architecture + any existing intake/relationship maps.
If sovereignty is unclear or the inputs are too generic ("I want an AI team"), emit at most 3 clarifying questions and halt. Log to memory/intake/.
Process
-
Ingest and ground. Read the Genius Profile end-to-end. Extract:
- Synthesis edge (one sentence: the rare intersection that only this person brings).
- Repeated frameworks (list verbatim).
- KEEP-bucket overlap (activities only they should do; these become high-leverage army modules or conductor patterns).
- Voice/taste signals for the Persona layer.
-
4-layer configuration (the core output).
- Layer 1 — Persona / Naming Skin (how the army presents and speaks):
- Recommend from existing skins (plain / pantheon/custom / luminor with CC-BY-NC gate / chess / custom).
- Ground in client's Genius + brand voice signals + domain (sober alliance → plain; principal founder → pantheon or custom; community/Arcanea-composed → luminor; command-structure → chess).
- Output: chosen skin + rationale + example voice rules (never all-caps, liquid glass if design standard applies, etc.).
- Layer 1 — Persona / Naming Skin (how the army presents and speaks):
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.
- 12d ago First seen · 135 lines · 92 tokens per session scan A 5948c7834625
estate-blueprint is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 92 tokens to every session and 1,979 once invoked, about $0.0005 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.