vibeshell AGENTS.md

A project guide for VibeShell, a desktop SSH and SFTP terminal built with a Rust backend and a React frontend. It documents the application structure and how its frontend communicates with its backend.

In plain words
What is it for?
Use it when working on VibeShell features involving SSH, SFTP, terminals, tunnels, session recording, local shells, AI tools, the React interface, or the Rust backend.
Why use it?
It gives coding agents the project’s architecture and important library constraints before they change the code. This reduces the chance of placing logic in the wrong layer or using incompatible SSH behavior.

Instructions file for CodexOpenCode

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/veithly/vibeshell/agents-md
Clone the repo
git clone --depth 1 https://github.com/veithly/vibeshell

Made for: Codex, OpenCode.

Per session 1,840 This file is loaded in full into every session.
When invoked 1,840 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 $0.01840 $0.01840
Opus 5 $0.00920 $0.00920
Sonnet 5 $0.00368 $0.00368
Haiku 4.5 $0.00184 $0.00184

Measured 2d ago against content hash 713f217503e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vibeshell 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 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.

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 · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VibeShell — Agent Guide

Overview

VibeShell is a modern SSH/SFTP desktop terminal built with Tauri 2 (Rust backend) and React 18 (TypeScript frontend). It supports multi-session SSH, SFTP file management, SSH tunneling, local shell, session recording, jump hosts, and AI tool integration.

Architecture

┌─────────────────────────────────────────────────────────┐
│  Frontend (React 18 + Vite 6 + TypeScript)              │
│  ├── Zustand stores (10 stores)                         │
│  ├── xterm.js terminal emulator                         │
│  └── Tailwind CSS (Tokyo Night theme)                   │
├─────────────────────────────────────────────────────────┤
│  IPC: Tauri invoke (frontend↔backend)                   │
│  IPC: Named pipe / Unix socket (CLI↔backend)            │
├─────────────────────────────────────────────────────────┤
│  Backend (Rust / Tauri 2)                               │
│  ├── SSH: russh 0.44 (async, non-Clone Handle/Channel)  │
│  ├── SFTP: russh-sftp                                   │
│  ├── DB: rusqlite (SQLite, bundled)                     │
│  ├── Async: tokio runtime                               │
│  └── Local Shell: portable-pty                          │
└─────────────────────────────────────────────────────────┘

Critical Knowledge

russh 0.44 Constraints

  • client::Handle<H> and Channel<S> are NOT Clone
  • Handle sharing: wrap in Arc<tokio::sync::Mutex<Option<Handle>>>
  • Channel I/O: use channel.into_stream()tokio::io::split() for bidirectional data

Frontend → Backend Communication

  • All Tauri calls go through src/lib/tauri.tssafeInvoke<T>(command, args)
  • Returns InvokeResult<T> = { success: true; data: T } | { success: false; error: TauriError }
  • For latency-sensitive input: use sendInputBatched() with RAF batching
  • For fire-and-forget: use fireAndForgetInvoke()

Session Lifecycle

SessionManager.create_with_credentials()
  → SshClient.connect_password/connect_key()
  → SshClient.open_shell()
  → Session { input: mpsc::Sender, output: broadcast::Sender }
  → Frontend attaches via Tauri event listener

Read the full file on GitHub · 164 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. 2d ago First seen · 164 lines · 1,840 tokens per session scan A 713f217503e3

Subscribe to this mod's changes

vibeshell AGENTS.md is an instructions file published in the GitHub repository veithly/vibeshell (76 stars, last pushed 5d ago), licensed MIT. It adds 1,840 tokens to every session, about $0.0092 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 2026-08-30.