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/creator-pipeline)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/creator-pipeline"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/creator-pipeline/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/creator-pipeline"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/creator-pipeline.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 | $0.02414 |
| Opus 5 | $0.00000 | $0.01207 |
| Sonnet 5 | $0.00000 | $0.00483 |
| Haiku 4.5 | $0.00000 | $0.00241 |
Grade A, and why
creator-pipeline 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/creator-pipeline
Load SIP.md, VERTICALS.md, VOICES.md, genius/profile-<person-slug>.md, genius/freedom-path-<person-slug>.md, and any brand/voice files under creator/brand-<person-slug>.md or creator/voice-<person-slug>.md if they exist. Generate a multi-modal content pipeline grounded in the person's Genius Profile — not generic content themes.
Input
$ARGUMENTS
When this command fires
- A person has completed
/discover-geniusand has a Genius Profile on file. - They want to turn frameworks → content stream, not one-off posts.
- They want attestation-aware production (every piece ships with "Built on SIP" or sidecar).
When this command does NOT fire
- No Genius Profile exists → halt and route to
/discover-genius. - Single artifact being shipped → use
/sip-attest(or modality-specific attest) directly. - Pillar already has 3+ pieces shipped and needs a reusable template → use
/content-systemize.
Process
-
Validate Genius Profile exists.
- Resolve
<person-slug>from<person-name>(lowercase, hyphenated). - Check for
genius/profile-<person-slug>.md. - If not present, halt with:
Run /discover-genius <person> first — content pipeline without genius excavation ships generic content. - Parse optional cadence arg (default
weekly) and modalities list (defaulttext,image).
- Resolve
-
Extract seed concepts from Frameworks list.
- Each framework in the Profile becomes a potential content seed.
- Typical shape: 5-10 frameworks → 50-100 pieces of content over 6 months.
- Map:
- Framework 1 → Pillar 1 (primary content theme)
- Framework 2 → Pillar 2
- ...
- Cross-domain synthesis (what only this person can say) → Flagship content
- If Profile has fewer than 3 frameworks, halt:
Profile too thin — run /discover-genius to deeper pass before pipelining.
-
Modality fit per pillar.
- For each pillar, read the Profile's voice samples and recommend modalities:
- Voice samples heavy on written prose → lead with text + image derivatives
- Voice samples heavy on spoken/conversational → lead with audio/podcast + text transcripts
- Framework inherently visual (process diagrams, mental models) → lead with image + video
- Framework story-driven → lead with audio/podcast + essay
- Intersect with requested modalities arg. Never force a modality the profile does not support — note it as "experimental" if requested but not voice-aligned.
- For each pillar, read the Profile's voice samples and recommend modalities:
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 · 188 lines · 0 tokens per session scan A afe94e0b1c57
creator-pipeline 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 2,414 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.