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/capture-daily)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/capture-daily"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/capture-daily/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/capture-daily"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/capture-daily.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 | $0.00057 | $0.01586 |
| Opus 5 | $0.00028 | $0.00793 |
| Sonnet 5 | $0.00011 | $0.00317 |
| Haiku 4.5 | $0.00006 | $0.00159 |
Grade A, and why
capture-daily 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/capture-daily
Load SIP.md, VOICES.md, agents/starlight-secondbrain.md, skills/memory/capture-discipline/SKILL.md. Facilitate a daily capture routine for the named person. Route each capture to its namespace or to the inbox. Save the day's captures to second-brain/captures/<person-slug>/<YYYY-MM-DD>.md.
The rule is 10 minutes. If it takes longer, the architecture is wrong — not the person.
Input
$ARGUMENTS
When this command fires
- Once per day (typical), as either end-of-day batch or throughout-the-day interactive
- Person has completed
/reclaim-knowledge(or declined to — SBIS works without reclamation, it just works better with) - Person has a Genius Profile or is willing to operate without one
When this command does NOT fire
- Fancy note-taking wanted. This is capture, not polish. Polish is
/distill-insights. - Weekly review — use
/orchestrate-brain - Monthly / quarterly distillation — use
/distill-insights
Process
-
Greet + name the session. Person name from
$ARGUMENTS. Today's date from current date. Acknowledge mode (interactive vs batch). -
Prompt through capture moments. Ask the person in their own voice:
"What came up today worth keeping?
- Any meetings or calls with an insight worth surviving? (One line per meeting.) - Any creative ideas — content, framework, aesthetic? - Any operational lessons — what worked, what broke, what to change next time? - Any patterns you noticed — something you've now seen more than once? - Anything on the edge of the Genius Profile — a framework that's refining itself, or a new one emerging?
Drop each one as it comes. One sentence. I'll route."
Do not push for volume. Some days have one capture. Some have none. "Nothing today" is a valid answer — do not force.
-
Route each capture. For every capture, apply the routing table from
skills/memory/capture-discipline/SKILL.md:Capture type Destination Strategic (decision, opportunity, trade-off) personal/<slug>/strategic-vault.mdCreative (content, aesthetic, narrative) personal/<slug>/creative-vault.mdOperational (what worked, what broke) personal/<slug>/operational-vault.mdPattern noticed personal/<slug>/wisdom-vault.mdGenius framework evolution second-brain/genius-evolution/<slug>.mdUnclear second-brain/inbox/
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 · 142 lines · 57 tokens per session scan A 67a07348a296
capture-daily is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 1,586 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
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.