What is claude-bridge AGENTS.md?

Instructions for using claude-bridge, a system that lets coding agents on a laptop and a VPS coordinate and transfer files.

Use it to send tasks or messages between local and VPS agents, receive replies, wait for updates, and move files with checksum verification.

It explains the separate conversation and file-transfer channels needed when two machines share development work.

How kadaba/claude-bridge configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to kadaba/claude-bridge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/kadaba/claude-bridge/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/kadaba/claude-bridge

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/kadaba/claude-bridge/agents-md/github.svg)](https://agentmods.dev/instructions/kadaba/claude-bridge/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/kadaba/claude-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/kadaba/claude-bridge/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/kadaba/claude-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/kadaba/claude-bridge/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,505 This file is loaded in full into every session.

When invoked 1,505 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.01505	$0.01505
Opus 5.5	$0.00602	$0.00602
Sonnet 5.5	$0.00301	$0.00301
Haiku 4.5	$0.00151	$0.00151

Measured 2mo ago against content hash ad99f0cd90ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-bridge AGENTS.md 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 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.

AGENTS.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — using claude-bridge from any AI coding CLI

This repo lets two AI coding-CLI sessions — one on your laptop, one on your VPS — collaborate: coordinate with each other and move files between the two machines with checksum verification.

It is not Claude-only. Any shell-capable agent works: Claude Code, OpenAI Codex, Grok CLI, or anything that can run bash. Codex reads this AGENTS.md automatically; for other tools, point the agent at this file.

You are one of two peers. Your identity is local (laptop) or vps.

Two independent channels

1. Coordination (the conversation)

How the two sessions talk. Pick whichever your tool supports:

Claude Code → native Remote Control (ListAgents + SendMessage). See skill/bridge-sync/ and skill/bridge-push/.
Any tool (Codex, Grok, …) → the relay, a neutral HTTP+SQLite message bus. Both sessions run bridge (a stdlib Python CLI) against one relay.py on the VPS:
```
bridge send --to vps  "message"      # or --to local
bridge send --to vps --kind task "do X"
bridge recv                          # pull new messages
bridge wait --timeout 300            # block until a reply arrives
```
Setup: run relay.py on the VPS, tunnel it (ssh -N -L 8787:127.0.0.1:8787 vps), and setup.sh on each machine. See README.md and PROTOCOL.md.

PROTOCOL.md is the tool-agnostic rulebook for the handshake (identify, hand off a task, report results, converge). Follow it regardless of which tool you are.

2. File transfer (the bytes) — same for every tool

Plain SSH; nothing tool-specific. Scripts in skill/bridge-push/scripts/:

bridge-init.sh <host> <user> <alias> <app-dir> — one-time: set up passwordless SSH from the laptop to the VPS (generates a key, installs it, writes an alias).
bridge-transfer.sh <src> <ssh_host> <dest> [--delete] — the atomic op: opens ONE ssh connection, transfers (rsync/tar), verifies every file's checksum on the VPS, then closes the connection. Exit 0 = VERIFIED, 1 = MISMATCH.
bridge-manifest.sh <path> — FILES/BYTES/SHA fingerprint (compare two copies).
bridge-recv-prep.sh <dest> — VPS side: create dest, report free space.

Read the full file on GitHub · 114 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.

2mo ago First seen · 114 lines · 1,505 tokens per session scan A ad99f0cd90ca

Subscribe to this mod's changes

claude-bridge AGENTS.md is an instructions file published in the GitHub repository kadaba/claude-bridge (3 stars, last pushed 2mo ago), licensed MIT. It adds 1,505 tokens to every session, about $0.0060 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.

Building agents ai ai-agent ai-agents ai-coding ai-tools claude

claude-bridge AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-bridge AGENTS.mdkadaba/claude-bridge	Instructions file	3	2mo ago	MIT	A	1,505	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	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	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

claude-bridge: Instructions file for Codex