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/alliance-decide)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/alliance-decide"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/alliance-decide/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/alliance-decide"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/alliance-decide.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 | $0.00028 | $0.00772 |
| Opus 5 | $0.00014 | $0.00386 |
| Sonnet 5 | $0.00006 | $0.00154 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
alliance-decide 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 9d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/alliance-decide
Load alliance SKILL.md, AGENTS.md, MEMORY.md, and SIP.md § 5 (sovereignty clause). The alliance has hit a fork. Your job is to surface the structural trade-off, force a call, and prevent drift.
Fork
$ARGUMENTS
Process
-
Frame the fork. Two paths. Maximum three. Mutually exclusive. If the input describes three independent questions, split and run separately — do not fuse.
-
Cost matrix. For each path:
- Time cost. How long until this path ships?
- Optionality cost. What doors close? Which future moves become harder or impossible?
- Reversibility cost. Can this be undone, and at what price?
-
Node positions. Each voice ≤3 sentences. Which path, why, from that node's frame. A node may abstain if the fork is not in their domain — "I don't have skin in this fork" is valid. Do not manufacture positions.
-
Decision rights. Name the one node that owns this call per the domain map in
MEMORY.md. If no node clearly owns it, emit:→ domain map gap; reshape before deciding, and default the call to the architect voice (usually the substrate-layer owner). -
Call. Either:
- Decision: named path, owner, ship date.
- Delay cost: if the owner chooses not to decide now, compute the cost of delay — "Not deciding by costs ." Name it.
-
Writeback. Append to Notion Decision Log with all fields. Update
MEMORY.md§ Open forks (remove if decided; keep with new decide-by date if delayed).
Output shape
# Alliance Decision — <alliance-name> · Fork <N>
**Fork:** <statement>
## Paths
- **A:** <one line>
- **B:** <one line>
## Cost matrix
| | Path A | Path B |
|----------------|--------|--------|
| Time | | |
| Optionality | | |
| Reversibility | | |
## Positions
**<node-1> (<role>):** <path + ≤3 sentences>
**<node-2> (<role>):** <path + ≤3 sentences>
…
## Decision rights
<Node>. Rationale: <one line tied to domain map>
## Call
<Path chosen, owner, ship date>
— OR —
Delay cost: not deciding by <date> costs <concrete loss>.
---
**Built on SIP** · <alliance-name> · Decision Log · <date>
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.
- 9d ago First seen · 78 lines · 28 tokens per session scan A 65714ef87e98
alliance-decide is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 772 once invoked, about $0.0001 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.