Borrowing it
Nothing to install: this file belongs to GiuseppeScottoLavina/crossbus. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/GiuseppeScottoLavina/crossbus/master/GEMINI.mdgit clone --depth 1 https://github.com/GiuseppeScottoLavina/crossbusWrote 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/instructions/giuseppescottolavina/crossbus/gemini-md)<a href="https://agentmods.dev/instructions/giuseppescottolavina/crossbus/gemini-md"><img src="https://agentmods.dev/badge/instructions/giuseppescottolavina/crossbus/gemini-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80Γ15 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/instructions/giuseppescottolavina/crossbus/gemini-md"><img src="https://agentmods.dev/badge/instructions/giuseppescottolavina/crossbus/gemini-md.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 | $0.02064 | $0.02064 |
| Opus 5.5 | $0.00826 | $0.00826 |
| Sonnet 5.5 | $0.00413 | $0.00413 |
| Haiku 4.5 | $0.00206 | $0.00206 |
Grade A, and why
crossbus GEMINI.md scanned grade A with 0 findings against 26 rules in 11 categories β prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency β measured 2mo 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 β 290 lines β stays where its author put it; the contents beside it link to each section on GitHub.
GEMINI.md - AI Agent Instructions for CrossBus
For AI Agents: This document contains specific instructions for working effectively with CrossBus.
IMPORTANT GLOBAL RULE:
ALWAYS use English for code, documentation, comments, and websites. Italian is for CHAT ONLY with the user. Even if the user speaks Italian, your output artifacts must be in English.
π― What is CrossBus
CrossBus is a library for cross-context communication in browsers:
- Iframes β Parent: PostMessageTransport
- Tab β Tab: BroadcastChannelTransport
- Main β Worker: PostMessageTransport
- Browser β Server: WebSocketTransport
- WebView β Native App: NativeBridgeTransport
π Quick Reference for AI Agents
Hub Pattern (Orchestrator)
import { CrossBus, PostMessageTransport } from 'crossbus';
const hub = new CrossBus({ isHub: true, peerId: 'hub', allowedOrigins: ['*'] });
// Connect iframe
const iframe = document.getElementById('my-iframe');
hub.addTransport(new PostMessageTransport(iframe.contentWindow, {
targetOrigin: '*'
}), { peerId: 'agent-1' }); // Specify remote peer ID
// Handle requests
hub.handle('getData', async (payload) => {
return { data: await fetchData(payload.id) };
});
Agent Pattern (Spoke)
import { CrossBus, PostMessageTransport } from 'crossbus';
const agent = new CrossBus({ peerId: 'agent-1', allowedOrigins: ['*'] });
agent.addTransport(new PostMessageTransport(window.parent, {
targetOrigin: '*'
}), { peerId: 'hub' }); // Specify remote peer (hub)
// Request data from hub
const result = await agent.request('hub', 'getData', { id: 5 });
Multi-Tab Sync Pattern
import { CrossBus, BroadcastChannelTransport } from 'crossbus';
const bus = new CrossBus({ peerId: `tab-${Date.now()}`, allowedOrigins: ['*'] });
bus.addTransport(new BroadcastChannelTransport('my-app-channel'), { peerId: '*' });
bus.on('sync', (event) => console.log('Received:', event.data));
bus.signal('sync', { message: 'Hello tabs!' });
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.
- 2mo ago First seen Β· 290 lines Β· 2,064 tokens per session scan A 56f985092486
crossbus GEMINI.md is an instructions file published in the GitHub repository GiuseppeScottoLavina/crossbus (5 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 2,064 tokens to every session, about $0.0083 per session on Opus 5.5. 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.
crossbus GEMINI.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| crossbus GEMINI.mdGiuseppeScottoLavina/crossbus | Instructions file | 5 | 7mo ago | Apache-2.0 | A | 2,064 | Gemini CLI |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |