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/culture-onboarding-90)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/culture-onboarding-90"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/culture-onboarding-90/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/culture-onboarding-90"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/culture-onboarding-90.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 | $0.00101 | $0.03854 |
| Opus 5 | $0.00051 | $0.01927 |
| Sonnet 5 | $0.00020 | $0.00771 |
| Haiku 4.5 | $0.00010 | $0.00385 |
Grade A, and why
culture-onboarding-90 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 12d 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/culture-onboarding-90
Load SIP.md, VOICES.md, agents/starlight-culture.md, skills/people-intelligence/culture-design.md. Produce a 90-Day Onboarding Architecture.
Why this matters
The first 90 days predict retention better than the entire interview process (research consistent across Buffer, GitLab, Bridgewater, Microsoft, Google internal data). The mechanisms are neurological: first impressions establish baseline cortisol response (Eisenberger / Lieberman — high-cortisol day-one predicts year-one departure), early belonging activation correlates with 12-month engagement, and wins shipped in week 1 correlate strongly with 12-month retention. Most orgs treat onboarding as paperwork + a buddy lunch and wonder why their year-one attrition is high.
Input
$ARGUMENTS
Flags
--size <S|M|L>— S = under 50, M = 50-250, L = 250+. Onboarding scaffolding shifts by size (S = mostly manager-driven; L = handbook + manager + buddy).--pattern <onsite|hybrid|remote>— physical pattern fundamentally changes onboarding architecture. Remote/hybrid requires written-first.--org <org-slug>— for save path.- Optional context paragraph — role specifics, team context, recent attrition patterns in this role.
Process
- Diagnose role context — what does success look like at day 90 for this role? What does failure look like at day 30?
- First day architecture — psychological safety + belonging activation. Manager script + welcome ritual + first-day artifact + environment readiness.
- First week architecture — structured 1:1s + role context + early win shipped + feedback loop.
- First month architecture — ramp plan + team integration + performance baseline.
- First quarter architecture — autonomous performance + cultural integration check + first formal feedback loop + retention-risk signal review.
- Written-first elements — handbook, role context doc, decision log, team faces. Required for remote/hybrid.
- Manager script — exactly what the manager says day 1, day 7, day 30, day 90.
- New-hire prep doc — what they need before day 1.
- Retention metric tie — explicit linkage to 12-month retention probability + measurement protocol.
- Save — write to
people-intelligence/culture/onboarding-90-<role>-<date>.md. - Hand off — exactly one named next move.
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.
- 12d ago First seen · 281 lines · 101 tokens per session scan A e7c195daa067
culture-onboarding-90 is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 101 tokens to every session and 3,854 once invoked, about $0.0005 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.
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.
forget
Delete specific memories.
learn
Add new learning to memory.