agentmods.dev

claude-bridge AGENTS.md

claude-bridge AGENTS.md is an instructions file for Codex, OpenCode from kadaba/claude-bridge. It costs 1,505 tokens per session, scanned A, original, MIT.

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

In plain words
What is it for?
Use it to send tasks or messages between local and VPS agents, receive replies, wait for updates, and move files with checksum verification.
Why use it?
It explains the separate conversation and file-transfer channels needed when two machines share development work.

Instructions file for CodexOpenCode

not rated 3 19d ago A scan 1,505 tokens original MIT
View the source file kadaba/claude-bridge
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/kadaba/claude-bridge/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.

agentmods badge for claude-bridge AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kadaba/claude-bridge/agents-md.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.svg" alt="Measured on agentmods" 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. 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.

ModelPer sessionOnce invoked
Fable 5 $0.01505 $0.01505
Opus 5 $0.00753 $0.00753
Sonnet 5 $0.00301 $0.00301
Haiku 4.5 $0.00151 $0.00151

Measured 3d ago against content hash ad99f0cd90ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

  1. 3d 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 19d ago), licensed MIT. It adds 1,505 tokens to every session, about $0.0075 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.

Building agentsaiai-agentai-agentsai-codingai-toolsclaude
Related

Other instructions, from other repositories

coograph brutal-honesty.instructions.md

Global communication style — applies to all workspaces and conversations.

paullukic/coograph · 414 tokens

tidyfactor-design AGENTS.md

Instructions for alwkala/tidyfactor-design, covering ⚡ skill & 24 modular slash commands (7 lifecycle stages) and critical architecture (non-negotiable).

alwkala/tidyfactor-design · 1,894 tokens

agent-notify AGENTS.md

AGENTS.md instructions for Akash97p/agent-notify, covering agentnotify agent workflow, start or resume work, local git workflow, required quality gates and architecture and security guardrails.

Akash97p/agent-notify · 738 tokens

claude-code-second-brain AGENTS.md

Instructions for shofer-dev/claude-code-second-brain, covering agents.md, read first, invariants and working here.

shofer-dev/claude-code-second-brain · 513 tokens

AmbyKit CLAUDE.md

Instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.

ambystechcom/AmbyKit · 257 tokens

loadout CLAUDE.md

Instructions for AmElmo/loadout, covering loadout, project structure, tech stack, key commands and test fixtures.

AmElmo/loadout · 1,780 tokens