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/design-alliance-readiness)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/design-alliance-readiness"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/design-alliance-readiness/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/design-alliance-readiness"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/design-alliance-readiness.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 | $0.00064 | $0.02511 |
| Opus 5 | $0.00032 | $0.01256 |
| Sonnet 5 | $0.00013 | $0.00502 |
| Haiku 4.5 | $0.00006 | $0.00251 |
Grade A, and why
design-alliance-readiness 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 11d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design-alliance-readiness
Load SIP.md, ALLIANCE.md, VOICES.md, agents/starlight-relational.md, skills/relational/alliance-readiness.md, and the person's relational/network-<person-slug>.md if it exists. Assess whether the named candidate is ready to forge into a SIP alliance with the person. Run the four forging conditions from ALLIANCE.md with rigor. Produce readiness score + recommendation. Do not forge.
Input
$ARGUMENTS
When this command fires
- A candidate was surfaced via
/map-relationships(alliance-surface step) and the person wants a rigorous assessment before forging - The person explicitly names a candidate: "Is X ready for an alliance?" / "Should we forge with Miguel?"
- A candidate has been developing over a quarter and the person wants to re-assess after previous "develop first" verdicts
When this command does NOT fire
- Before network mapping — if the candidate was not surfaced through a mapped architecture, the assessment is based on hope rather than structure. Run
/map-relationshipsfirst. - For general "should I have partners" questions — this command assesses a named candidate, not a category.
- At
/alliance-forge— Forge runs its own condition validation. This command is the pre-filter, not a duplicate. If all four conditions pass here, hand off to Forge; do not re-run this command as part of Forge.
Process
-
Validate inputs.
- Resolve
<candidate-name>from$ARGUMENTS. If no candidate named → halt: "Name the specific candidate. Alliance-readiness is assessed per relationship, not in the abstract." - Attempt to read
relational/network-<person-slug>.md. If missing, emit one-line notice: "Network map not found — proceeding from candidate context alone. Recommend running /map-relationships first for fuller architecture." Continue only if candidate context is rich enough; otherwise halt and route to/map-relationships.
- Resolve
-
Pre-filter (two baseline facts).
- Active trust. Is trust current, not historical, not inherited? If dormant or thin → halt with "Trust-building is the prerequisite. Name a trust-building artifact (joint project, regular conversation, shared problem) and a 2-quarter timeline before re-assessing."
- Complementary domains at surface glance. Does the candidate hold a layer the person does not? If domains look identical or one subsumes the other → halt with "No alliance shape available. Consider services contract, referral partnership, or parallel-but-independent work."
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.
- 11d ago First seen · 192 lines · 64 tokens per session scan A fc8cf4caf9d3
design-alliance-readiness is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 2,511 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.
consolidate
Write a compact checkpoint summary of the current frontier.