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/tax-sanity)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/tax-sanity"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/tax-sanity/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/tax-sanity"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/tax-sanity.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 | $0.00056 | $0.03094 |
| Opus 5 | $0.00028 | $0.01547 |
| Sonnet 5 | $0.00011 | $0.00619 |
| Haiku 4.5 | $0.00006 | $0.00309 |
Grade A, and why
tax-sanity 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 8d 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.
/tax-sanity
Load SIP.md, VOICES.md, agents/starlight-business.md, skills/business/entity-architecture.md, skills/business/revenue-modeling.md, and if present the person's Genius Profile and any existing business/entity-<slug>.md or business/revenue-<slug>.md. Produce a Tax Readiness Checklist. Hand off to exactly one next move — usually: book the accountant.
Disclaimer (non-waivable — heavier than elsewhere)
This is thinking architecture, not tax advice.
- Tax is jurisdiction-specific and rule-specific. Rules change. Interpretations vary. Penalties are real.
- This command does not give tax advice and cannot give tax advice.
- Real decisions about your taxes require a qualified tax professional (accountant, tax attorney, Steuerberater, fiscalist, CPA, etc.) licensed in your jurisdiction.
- If any output of this command contradicts what your qualified professional tells you, trust the professional. They know the rules; this command knows the questions.
What this command does: It walks you through the common tax-adjacent questions a sovereign founder should be thinking about before the accountant meeting, so the meeting is specific, efficient, and reveals the right moves. Nothing here is a recommendation to take or skip any tax action.
Input
$ARGUMENTS
Flags
--jurisdiction <NL|US-DE|US-CA|US-other|UK|DE|other|agnostic>— required to make the checklist usable. Ifagnostic, every jurisdictional note carries a<jurisdiction-specific>placeholder.
Process
-
Disclaim, heavily. Open with the full disclaimer above. Not negotiable; the tax layer requires more friction before the user proceeds.
-
Locate context. Read jurisdiction flag. Load any existing
business/entity-<slug>.mdandbusiness/revenue-<slug>.mdif present — they inform the tax questions that apply. -
Walk the six question groups (below). For each group, produce the questions the person should think about, and the corresponding question the accountant can actually answer.
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.
- 8d ago First seen · 256 lines · 56 tokens per session scan A b59b983ed7b6
tax-sanity is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 3,094 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 2026-09-03.
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.
performance
Generate a strategy performance report with key metrics.