Borrowing it
Nothing to install: this file belongs to frankxai/Starlight-Intelligence-System. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/frankxai/Starlight-Intelligence-System/main/.claude/commands/discover-genius.mdgit 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/discover-genius)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/discover-genius"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/discover-genius/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/discover-genius"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/discover-genius.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 | $0.00049 | $0.01495 |
| Opus 5 | $0.00024 | $0.00747 |
| Sonnet 5 | $0.00010 | $0.00299 |
| Haiku 4.5 | $0.00005 | $0.00150 |
Grade A, and why
discover-genius 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 10d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/discover-genius
Load SIP.md, VOICES.md, agents/starlight-genius.md, skills/intelligence/genius-excavation.md. Excavate the person's genius from the corpus they provide. Produce Genius Profile + Freedom Path. Hand off to exactly one downstream command.
Input
$ARGUMENTS
Process
-
Ingest. Identify the person. Collect corpus from the sources named in
$ARGUMENTS. If no corpus is provided — only a name or a free-text description — halt and return:"Need corpus to excavate. Provide 3–5 sources of your material (Canva, Google Drive, local Documents, Notion, screenshots, past posts/essays, recorded sessions). You do not need to send everything — just point me at representative samples from each source."
Do not proceed without corpus.
-
Recognize. Scan the corpus for repeated frameworks. A pattern is only named if it recurs ≥3 times across corpus items. Record observed-in sources for each framework.
-
Cross-reference. Identify the ≥2 fields this person blends. Name the compounding edge.
-
Voice-sample. Extract 10–15 distinctive words or phrases, and 5–7 real quotes from the corpus with source citations.
-
Sort. For every activity referenced in the corpus, assign exactly one bucket: KEEP / DELEGATE / AUTOMATE / KILL. All four buckets must be populated before synthesis.
-
Synthesize. Generate the two documents using the output shape below.
-
Save. Create
genius/directory if missing. Write:genius/profile-<slug>.mdgenius/freedom-path-<slug>.md
Where
<slug>is the person's name in kebab-case. Both files must include the "Built on SIP" attestation block. Personal-genius data lives in the person's instance only — do not write to any public vault. -
Hand off. Name exactly one next move from the downstream menu. Never two. Do not offer optionality.
Output format
# Genius Profile — <Person Name> — <YYYY-MM-DD>
## Signal (what only you uniquely see)
<2-3 sentences naming the lens only this person brings. Specific, not generic.>
## Frameworks you keep rebuilding (≥3)
1. **<framework name>** — <one-line description> (observed in: <sources>)
2. **<framework name>** — <one-line description> (observed in: <sources>)
3. **<framework name>** — <one-line description> (observed in: <sources>)
## Distinctive vocabulary (fingerprint)
- "<word/phrase>" — <context of use>
- "<word/phrase>" — <context of use>
- (10–15 items total)
## Cross-domain synthesis (your compounding edge)
**<Field A> × <Field B> [× <Field C>]** = <the resulting unique edge, named in the person's register>
## Voice samples (how you uniquely say it)
1. "<direct quote>" — <source>
2. "<direct quote>" — <source>
3. "<direct quote>" — <source>
4. "<direct quote>" — <source>
5. "<direct quote>" — <source>
(5–7 items total)
---
# Freedom Path — <Person Name> — <YYYY-MM-DD>
## KEEP (genius work — only you can do)
- <task/activity>
- <task/activity>
- ...
## DELEGATE (executor work — anyone trained can do)
- <task/activity>
- <task/activity>
- ...
## AUTOMATE (system work — AI/workflow can do)
- <task/activity>
- <task/activity>
- ...
## KILL (compounds nothing — stop doing)
- <task/activity>
- <task/activity>
- ...
## Next moves
1. Handover executor onboarding → `/train-executor <executor-name>` (from DELEGATE bucket)
2. Content pipeline from frameworks → `/creator-pipeline` (from KEEP bucket, modalized)
3. Second-brain architecture → `/reclaim-knowledge` (organize what's been scattered)
4. Business-layer design → (future) `/build-business`
**Named next move for this person:** `/<command>` — <one-line rationale>
---
**Built on SIP** — Starlight Intelligence Protocol
- Substrate: starlightintelligence.org/protocol v1.1.0
- Layers used: [file-contract, attestation, commands, sovereignty]
- Verticals: [email protected] (GIS alpha)
- Generated: <ISO 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.
- 10d ago First seen · 130 lines · 49 tokens per session scan A 01d95f0a038a
discover-genius is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 1,495 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
agent
Create and manage custom AI agents.
memories
View and manage learned memories.
mpm-session-resume
Load context from paused session.
forget
Delete specific memories.
learn
Add new learning to memory.
learn
End-of-session learning loop — analyze signals, approve instincts, capture directives, refresh MEMORY.md. Invokes dreamteam learn; one source of behavioral truth shared with the team.md SESSION LEARNING step.