What is loopsy AGENTS.md?

Instructions for Loopsy, a system that lets AI coding agents on different machines communicate. It supports remote commands, file transfers, and shared key-value context between machines.

It helps coordinate coding agents across machines, run remote commands, browse or transfer files, and share context with one or more peers.

It gives agents a defined way to discover peers, check their status, exchange files, and share information across computers.

loopsy AGENTS.md — Instructions file by leox255

Install

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.

agentmods

npx agentmods add instructions/leox255/loopsy/agents-md

Clone the repo

git clone --depth 1 https://github.com/leox255/loopsy

Made for: Codex, OpenCode.

Per session 4,108 This file is loaded in full into every session.

When invoked 4,108 The same file — it is already loaded in full.

Security scan A 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.04108	$0.04108
Opus 5	$0.02054	$0.02054
Sonnet 5	$0.00822	$0.00822
Haiku 4.5	$0.00411	$0.00411

Measured 2d ago against content hash f076f7b1ef80, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

loopsy AGENTS.md scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **MCP tools**: If MCP tools (`loopsy_context_set`, etc.) are working, use them. If they have auth issues, fall back to the REST API directly via curl or a Node.js script

AGENTS.md · 406 lines

How it starts

The opening of the file, as written. The whole thing — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Loopsy - Cross-Machine Communication for AI Coding Agents

What is Loopsy?

Loopsy enables AI coding agent instances (Claude Code, Gemini CLI, Codex CLI, etc.) on different machines to communicate. You can:

Run commands on remote machines
Transfer files between machines
Share context (key-value state) between AI coding agent instances

Setup

Run loopsy init on each machine to generate config and API key
Run loopsy start on each machine to start the daemon
Exchange API keys between machines (add to ~/.loopsy/config.yaml under auth.allowedKeys)
Peers auto-discover via mDNS, or add manually: loopsy peers add <ip>

MCP Tools Available

When the Loopsy MCP server is running, you have these tools:

loopsy_list_peers - See all machines on the network
loopsy_execute - Run a command on a remote machine
loopsy_transfer_file - Push/pull files between machines
loopsy_list_remote_files - Browse files on a remote machine
loopsy_context_set - Store shared state on a peer
loopsy_context_get - Retrieve shared state from a peer
loopsy_peer_status - Check a peer's health
loopsy_broadcast_context - Set context on ALL peers
loopsy_context_list - List context entries with optional prefix filter
loopsy_context_delete - Delete a context entry by key
loopsy_send_message - Send a protocol-compliant message to a peer (handles envelope, inbox key, outbox copy, TTL)
loopsy_check_inbox - Check your inbox for new messages
loopsy_ack_message - Acknowledge a received message (see Known Issues)
loopsy_check_ack - Check if a peer has acknowledged your messages

Messaging Protocol v1

This section defines the standard protocol for AI coding agent instances to communicate reliably across machines. Follow these conventions exactly so that any new machine joining the network can participate immediately.

Key Concepts

Inbox: Messages addressed to you, stored on YOUR machine by the sender
Outbox: Local copies of messages you sent, stored on YOUR machine
ACK: Acknowledgment that a message was read, stored on the SENDER's machine by the receiver

Read the full file on GitHub · 406 lines

Changes

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.

2d ago First seen · 406 lines · 4,108 tokens per session scan A f076f7b1ef80

Subscribe to this mod's changes

loopsy AGENTS.md is an instructions file published in the GitHub repository leox255/loopsy (139 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 4,108 tokens to every session, about $0.0205 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

loopsy AGENTS.md