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/compose-stackgit clone --depth 1 https://github.com/frankxai/Starlight-Intelligence-SystemWhat 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 | $0.00070 | $0.02328 |
| Opus 5 | $0.00035 | $0.01164 |
| Sonnet 5 | $0.00014 | $0.00466 |
| Haiku 4.5 | $0.00007 | $0.00233 |
Grade A, and why
compose-stack 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 2d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/compose-stack
Load SIP.md, docs/ARCHITECTURE.md, genius/profile-<slug>.md (REQUIRED — halt to /discover-genius if missing), genius/freedom-path-<slug>.md (REQUIRED — halt if missing). Load any already-shipped layer artifacts for this person if present: vision/vision-<slug>.md, second-brain/inbox-<slug>/, business/entity-plan-<slug>.md, health/regimen-<slug>.md, relational/network-<slug>.md, creator/pipeline-<slug>.md, wealth/dpi-<slug>.md. The stack is personalized, not generic — everything depends on reading the person first.
Input
$ARGUMENTS
Parse $ARGUMENTS for:
<person-name>— required. Slug = kebab-case of name.--priority=freedom|revenue|vision|compound— optional, defaultfreedom.--horizon=90-day|180-day|year— optional, default90-day.--include-spiritual— explicit opt-in only. Never auto-include.
Process
-
Load foundation. Read Genius Profile and Freedom Path for
<person-name>. If either is missing, halt immediately with:"No Genius Profile or Freedom Path on file for . The stack sequences around who this person uniquely is — generic plans re-scatter. Run
/discover-genius <person-name>first. That produces the foundation this command reads."Do not fabricate. Do not proceed on intent alone.
-
Diagnose entry state. Read both documents. Name the current bottleneck in two to three sentences. Use these signals:
- Scattered knowledge, can't find own work → Layer 2 (Second Brain) first
- Weak or unclear revenue, entity chaos → Layer 4 (Business) first
- No content system, frameworks stuck in head → Layer 5 (Creator) first
- Burnout, crashes, can't sustain output → Layer 7 (Health) first, cross-cutting
- Drift, no clear North Star → Layer 3 (Vision) first
- Isolation, no alliance-ready relationships → Layer 8 (Relational) first
- Indispensable-but-trapped, want to hand off → Freedom Path execution + Layer 5 train-executor
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.
- 2d ago First seen · 153 lines · 0 tokens per session scan A 1cd64208aff2
compose-stack is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed 2d ago), licensed MIT. It adds 70 tokens to every session and 2,328 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
plan-sprint
Create multiple tracks from a list of features — generates spec, plan, and metadata for each track in parallel.
cc-council
Comprehensive multi-agent council review with 6 protocols, 10 specialists, scoped scoring (per-scope thresholds and weights), state machine orchestration, auto-fix, and 50+ configuration flags.
create
Scaffold a new plugin with directory structure, manifests, and marketplace registration.
develop
Implement skill development issues with TDD-governed workflow.
release
Release the plugin — bump version across 4 files, then optionally commit, tag, push, and create a GitHub Release.
agentos-status
Show AgentOS system status — agents, workers, health.