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-forge)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/alliance-forge"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/alliance-forge.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 | $0.00040 | $0.00951 |
| Opus 5 | $0.00020 | $0.00476 |
| Sonnet 5 | $0.00008 | $0.00190 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade A, and why
alliance-forge 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 8d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/alliance-forge
Load SIP.md, ALLIANCE.md, AGENTS.md. Forge a new SIP alliance with full scaffold + compliance checks.
Input
$ARGUMENTS
Process
-
Validate the four forging conditions (per
ALLIANCE.md):- Skill complementarity: ask the user to name what each node uniquely holds. If any two nodes' domains overlap such that one could absorb the other, halt and recommend services contract instead.
- Non-zero-sum value: ask for one artifact the alliance will ship that none of the nodes could ship alone. If none, halt.
- Sovereignty is possible: ask for each node's declared domain. If domains collide on decision rights, halt and recommend domain reshaping.
- Attestation is wanted: confirm each node agrees to "Built on SIP" attribution on cross-node artifacts. If any node declines, halt.
-
Build the node declaration for each member. Enforce the full YAML schema from
ALLIANCE.md§ Node definition. Missing fields = node not ready; do not paper over. -
Scaffold the alliance repo structure:
<alliance-name>/
├── README.md — what this alliance is, members, cadence
├── SKILL.md — alliance protocol fingerprint
├── AGENTS.md — per-node voices (from starlight/AGENTS.md template)
├── MEMORY.md — cycle 0 state
└── .claude/commands/
├── alliance-reflect.md
├── alliance-decide.md
└── <alliance-name>-specific commands as needed
-
Write the alliance's
SKILL.md— names the alliance, lists nodes, references SIP version, declares cycle cadence and attestation commitment. -
Write the alliance's
AGENTS.md— map canonical voices (architect / sovereign-creator / protocol-defender / implementer / overseer) to declared nodes. Unfilled voices are visible gaps. -
Write the alliance's
MEMORY.md— cycle 0 state, active commitments (empty), open forks (empty), external IDs placeholders. -
Install alliance-scoped commands — copy
alliance-reflect.mdandalliance-decide.mdfromstarlight/.claude/commands/, customized with alliance name.
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.
- 8d ago First seen · 87 lines · 40 tokens per session scan A 25f1cb6ff45c
alliance-forge is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 951 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.