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-army-deploy)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/estate-army-deploy"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/estate-army-deploy/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-army-deploy"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/estate-army-deploy.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 | $0.00000 | $0.01208 |
| Opus 5 | $0.00000 | $0.00604 |
| Sonnet 5 | $0.00000 | $0.00242 |
| Haiku 4.5 | $0.00000 | $0.00121 |
Grade A, and why
estate-army-deploy 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/estate-army-deploy
Load the estate's 4-layer Blueprint, SIS-instance.md, current harness, steward runbooks, and SIP Swarm Operating Manual. Deploy or evolve the production runtime layer ("Steward as service" or self-hosted always-on).
This is the scale + run gate: move from Pilot (first live workflows) to Standing (24/7 reliable Mesh + Mind that compounds, self-heals, reports, and evolves without constant Frank babysitting).
Input
$ARGUMENTS
Subcommands
deploy (default)
- Provision runtime harness from starlight-estate-os + estate-tuned 20%:
- Steward daemon / task scheduling (drift detection, scheduled Proving Ground + Model Arena against this estate's patterns).
- Memory Bus hygiene + Veil + temporal decay enforcement in production.
- Claw activation: sentinel (secrets/identity), attestation (ambient "Built on SIP"), reclamation, bootstrap re-sync.
- /si + ORCHESTRATION_ENGINE routing surface live (handoff packets, receipts, cross-CLI).
- Cost plane + token telemetry hooks (initial baselines).
- Optional: cloud (Railway/VPS stub) or hybrid entrypoints; local-first default.
- Wire client-visible dashboard (metrics vs world-class E2E checklist: describe behavior, live attested work, memory value at horizon, runbooks, gates).
- Emit first Steward health baseline + report template.
- Output: "Estate deployed to Standing. Next health: . Dashboard at ." + attestation block.
scale
- Increase capacity / add lanes / new modules:
- Spin additional /si targets (e.g. more Antigravity/Codex workers) grounded in Topology.
- Expand Modules via /spawn-domain-stack (Genius KEEP + client Blueprint).
- Update Swarm Consensus thresholds, yolo scope, or council seats if Blueprint calls for it.
- Re-run promotion check: any new generalized pattern offered back to starlight-estate-os.
- Require board gate for topology/kernel changes (per invariants).
- Output: scaled manifest + updated Blueprint + new receipts.
health
- Execute full production health loop:
- Run drift, secret, identity, harness conformance against estate-specific baselines.
- Execute scheduled evals (Proving Ground on recent atoms, Model Arena head-to-head on estate tasks).
- Memory / attestation / cost plane audit.
- Self-healing trigger simulation.
- Compare to E2E checklist.
- Output: machine + human health report (JSON + MD) + remediation PR draft if issues.
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 · 84 lines · 0 tokens per session scan A ce37e0b2bec4
estate-army-deploy is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,208 tokens. 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.
agentic-jujutsu
The learning backbone of ACOS. Based on ruvnet's agentic-jujutsu (v2.3.6, MIT), customized for ACOS.