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/org-reorg-trauma-audit)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/org-reorg-trauma-audit"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/org-reorg-trauma-audit/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/org-reorg-trauma-audit"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/org-reorg-trauma-audit.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 | $0.00100 | $0.03858 |
| Opus 5 | $0.00050 | $0.01929 |
| Sonnet 5 | $0.00020 | $0.00772 |
| Haiku 4.5 | $0.00010 | $0.00386 |
Grade A, and why
org-reorg-trauma-audit 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 11d 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/org-reorg-trauma-audit
Load SIP.md, agents/starlight-org.md, skills/people-intelligence/org-architecture.md. Read any prior people-intelligence/org/ outputs and any Talent IS signals available. Produce a Reorg Trauma Audit + Sequencing Plan. May refuse the reorg outright. Hand off to exactly one next command.
Disclaimer (non-waivable)
Reorgs implicate severance, role classification, protected-class concentration in cuts (age, gender, race, disability, parental status, tenure), and jurisdictional employment-law variation. This document is structural thinking architecture, not legal advice. Real reorg decisions require qualified employment counsel before any communication or action.
The number you must hear first (non-negotiable)
McKinsey-class research consistently finds 70%+ of organizational reorganizations fail to deliver their promised outcomes. Roughly half create more dysfunction than they solve. This is not a hedge or a footnote. It is the design constraint this audit operates under.
The implication: if your reorg's case is shaky on its merits, the base rate says it will fail. The audit's job is to honestly tell you which side of that 70/30 your specific reorg sits on, and what would have to be true for it to land in the 30%.
Input
$ARGUMENTS
Flags
--reorg-scope <team|department|division|company-wide>— how much of the org the change touches. Larger scope = exponentially higher trauma cost.--proposed-timeline <weeks|months>— proposed announce-to-live window. Weeks = high-threat (closer to surprise). Months = sequencing room.
Process
-
Lead with the 70%+ failure rate. First thing the user reads. Not buried.
-
Vision-fit pre-check. Before any audit work, ask: is the underlying issue actually a vision problem? Symptoms suggesting yes: "we're not aligned," "teams are working at cross purposes," "we don't know what we are anymore," "the strategy keeps shifting." If yes, refuse to proceed with reorg sequencing and route to
/define-visionor substrate-level vision work. Reorg cannot fix vision drift; it amplifies it. Name this honestly even if the user pushes back.
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.
- 11d ago First seen · 256 lines · 100 tokens per session scan A 90a0aea36fe1
org-reorg-trauma-audit is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 3,858 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
lavra-checkpoint
Save session progress by filing beads, capturing knowledge, and syncing state.
bigproject
Large-scale project orchestration with Himawari (Atlas).
memories
View and manage learned memories.
mpm-init
Initialize or update project for Claude Code and MPM.
mpm-organize
Organize project files with intelligent consolidation.
mpm-ticket-view
Orchestrate ticketing agent for project management workflows.