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/orchestrate-brain)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/orchestrate-brain"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/orchestrate-brain/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/orchestrate-brain"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/orchestrate-brain.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 | $0.01766 |
| Opus 5 | $0.00024 | $0.00883 |
| Sonnet 5 | $0.00010 | $0.00353 |
| Haiku 4.5 | $0.00005 | $0.00177 |
Grade A, and why
orchestrate-brain 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orchestrate-brain
Load SIP.md, VOICES.md, agents/starlight-secondbrain.md, skills/memory/capture-discipline/SKILL.md, skills/memory/insight-distillation/SKILL.md. Run the weekly 30-minute second-brain review ritual for the named person. Save the review to second-brain/reviews/<person-slug>-weekly-<YYYY-MM-DD>.md.
Thirty minutes is the cap. Not the target, the cap. A weekly review that takes 60 minutes is a sign of weekly review neglect the week before — address by returning to the rhythm, not by making this session longer.
Input
$ARGUMENTS
When this command fires
- Once per week (typical cadence: same day each week — the fixed-day habit compounds)
- Person has captured throughout the week using
/capture-dailyor their own capture habit - Inbox has accumulated items needing routing decisions
When this command does NOT fire
- Monthly distillation — use
/distill-insights --window monthas a standalone 90-min session - Quarterly integration — use
/distill-insights --window quarteras a standalone half-day - Daily capture — use
/capture-daily - First-time setup — use
/reclaim-knowledgefirst, then start weekly reviews
The Five Phases (30 min total)
Phase 1: Inbox Clear (10 min)
-
Read all items in
second-brain/inbox/. -
For each inbox item, make a 10-second decision:
- Route → move to namespace per routing table (see
capture-discipline/SKILL.md) - Drop → delete; not every thought survives, and that's healthy
- Hold → explicitly note why you're holding; holds must justify themselves
- Route → move to namespace per routing table (see
-
Inbox must end at zero. If it doesn't, the routing rules are broken — note it in the review for next week.
Phase 2: Lightweight Distillation (10 min)
Invoke /distill-insights --person <name> --window week behavior at light depth:
- Load the week's captures (last 7 days across all namespaces + just-cleared inbox).
- Cluster by theme. Don't force clusters; some weeks have none.
- Count occurrences. Note clusters at ≥3 (eligible for framework draft) and at 2 (watch next week).
- Do not archive captures at weekly review. That's monthly's job. Just note the clusters.
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 · 158 lines · 49 tokens per session scan A 0131be38d5a2
orchestrate-brain 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 1,766 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.