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/architect-entitygit 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/architect-entity)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/architect-entity"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/architect-entity.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 | $0.00050 | $0.02830 |
| Opus 5 | $0.00025 | $0.01415 |
| Sonnet 5 | $0.00010 | $0.00566 |
| Haiku 4.5 | $0.00005 | $0.00283 |
Grade A, and why
architect-entity 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 6d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/architect-entity
Load SIP.md, VOICES.md, agents/starlight-business.md, skills/business/entity-architecture.md, and if present the person's Genius Profile (genius/profile-<slug>.md) and Freedom Path (genius/freedom-path-<slug>.md). Produce an Entity Architecture Plan. Hand off to exactly one next command.
Disclaimer (non-waivable)
This is thinking architecture, not tax/legal advice. Real decisions require a qualified professional in your jurisdiction.
This command organizes your thinking before you talk to a lawyer. It does not replace the lawyer. It does not prescribe an entity. It surfaces trade-offs and produces a checklist so the professional conversation is efficient and specific.
Input
$ARGUMENTS
Flags
--jurisdiction <NL|US-DE|US-CA|US-other|UK|DE|other|agnostic>— which jurisdiction the entity will operate in. Ifagnostic, output uses<jurisdiction-specific>placeholders throughout. If the person operates in multiple jurisdictions, pass the primary and flag multi-jurisdictional exposure in the optional context paragraph.--structure-type <solo|partnership|agency|holding>— what shape the business actually is:solo— one-person practice, one revenue stream or a few, no employeespartnership— two or more owners with shared ownershipagency— service business with contractors or employees, multiple clientsholding— multiple brands or operating companies, IP/asset separation question is live
Process
-
Disclaim. Open the output with the non-waivable disclaimer. Structurally first, always.
-
Locate. Confirm jurisdiction from
--jurisdictionflag. Confirm structure-type from--structure-typeflag. If jurisdiction isagnostic, explicitly flag that the Plan uses jurisdiction-placeholders and recommend re-running with a specific jurisdiction once chosen. -
Read. If a Genius Profile exists at
genius/profile-<slug>.md, read it and note KEEP/DELEGATE/AUTOMATE/KILL buckets — they inform whether an agency (many DELEGATE-bucket executors needed) vs solo (KEEP-bucket dominant) structure fits.
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.
- 6d ago First seen · 196 lines · 50 tokens per session scan A 20a9b846af24
architect-entity is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 2,830 once invoked, about $0.0003 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.
fd-checkpoint
Purpose: Force-save the current session to checkpoint.json and STATE.md so it can be safely resumed later with /fd-resume. Normally runs automatically on session.idle via the session-events hook; invoke manually to force a save before closing a session.