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.
npx agentmods add commands/frankxai/starlight-intelligence-system/org-spangit 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/org-span)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/org-span"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/org-span.svg" alt="Measured on agentmods" 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 | $0.00074 | $0.02824 |
| Opus 5 | $0.00037 | $0.01412 |
| Sonnet 5 | $0.00015 | $0.00565 |
| Haiku 4.5 | $0.00007 | $0.00282 |
Grade A, and why
org-span 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 5d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/org-span
Load SIP.md, agents/starlight-org.md, skills/people-intelligence/org-architecture.md. If org chart exists in repo or attached, read it. Produce a Span-of-Control Architecture Audit + Redesign. Hand off to exactly one next command.
Disclaimer (non-waivable)
This is structural thinking architecture, not employment-law advice. Span changes that involve reporting-line shifts, demotions, or de-layering may implicate severance, classification, and protected-class considerations. Real decisions require qualified employment counsel.
Input
$ARGUMENTS
Flags
--size <under-10|10-50|50-200|200-1000|1000+>— total headcount. Smaller orgs typically have fewer span issues; larger orgs accumulate them at predictable scale transitions.--growth-stage <stable|growing|scaling|hypergrowth>:stable— flat or declining headcount; span issues are typically calcifiedgrowing— 10-25% YoY headcount growth; span issues emerging at the founder/exec layerscaling— 25-50% YoY; classic top-heavy / middle-thin patternhypergrowth— >50% YoY; span issues are the dominant constraint
Research bounds (cite directly)
- Complex knowledge work: ~5-9 direct reports per manager
- Repetitive supervised work: up to 15-20 direct reports per manager
- Founder-CEOs in growth-stage: commonly over-span at 10-15 directs; cost shows as decision bottlenecks, neglected reports, founder burnout, and a "thin middle" because layer-1 directs absorb work that should belong to a layer-2 they don't have
- Pattern: most orgs over-span at the top (founder/execs), under-span in the middle (managers with 2-3 reports — too few to justify the management overhead), and have variable span at IC layer
Process
-
Disclaim.
-
Inventory current spans. For each manager (founder, execs, directors, managers):
- Count direct reports
- Classify work complexity per report (knowledge work / repetitive supervised / mixed)
- Note whether reports are themselves managers (creates a span-of-spans question — managing managers is more complex than managing ICs and tightens the bound)
- Time-allocation snapshot: how much of the manager's week goes to managing the directs vs other work?
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.
- 5d ago First seen · 196 lines · 74 tokens per session scan A 8e90494a8dcd
org-span is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 2,824 once invoked, about $0.0004 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
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.
consolidate
Write a compact checkpoint summary of the current frontier.