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.
npx agentmods add instructions/alexkerber/termaway/claude-mdgit clone --depth 1 https://github.com/alexkerber/termawayWrote 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/alexkerber/termaway/claude-md)<a href="https://agentmods.dev/instructions/alexkerber/termaway/claude-md"><img src="https://agentmods.dev/badge/instructions/alexkerber/termaway/claude-md.svg" alt="Measured on agentmods" 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 | $0.03272 | $0.03272 |
| Opus 5 | $0.01636 | $0.01636 |
| Sonnet 5 | $0.00654 | $0.00654 |
| Haiku 4.5 | $0.00327 | $0.00327 |
Grade C, and why
termaway CLAUDE.md scanned grade C 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 5d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/termaway-linux How it starts
The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project: TermAway
TermAway is a self-hosted terminal access solution. Your Mac terminal, on your iPad.
Commands
bun install # Install dependencies (fast)
node server/index.js # Start the server (http://localhost:3000)
node --watch server/index.js # Start with auto-reload
Note: node-pty requires Node.js runtime (not bun) due to native bindings.
Project Structure
termaway/
├── apps/
│ ├── ios/ # iOS/iPadOS app (SwiftUI + SwiftTerm)
│ ├── macos/ # macOS menu bar app (AppKit)
│ └── web/ # Web terminal client (xterm.js)
├── server/ # Node.js WebSocket server
├── website/ # Marketing site (Astro, termaway.app)
│ ├── src/
│ │ ├── components/ # Header, Footer
│ │ ├── layouts/ # Base layout
│ │ ├── pages/ # index, policy
│ │ └── styles/ # Global CSS
│ └── public/assets/ # Images, icons
└── builds/ # Release artifacts (.dmg, .tar.gz)
Architecture
This is a web-based terminal application that provides remote terminal access over WebSocket. It uses node-pty for pseudo-terminal emulation and xterm.js for browser rendering.
Server (Node.js)
-
server/index.js: Express HTTP server + WebSocket server. Handles client connections, routes WebSocket messages to session manager, and serves static files. Maps each WebSocket connection to a session via
wsSessionMap. -
server/sessionManager.js: Manages PTY sessions. Each session has:
- A node-pty process spawned with user's default shell (
$SHELL -l) - A scrollback buffer for reconnecting clients
- A set of attached WebSocket clients
- Sessions persist until explicitly killed or the shell exits
- A node-pty process spawned with user's default shell (
tmux persistence (opt-in)
With TERMAWAY_TMUX=1 (the macOS app's "Keep sessions running when the server
stops" preference), a session's PTY runs a tmux client instead of the login
shell, so the shell belongs to the tmux server and outlives this process.
adoptTmuxSessions() reattaches to everything still running at startup.
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.
- 5d ago First seen · 297 lines · 3,272 tokens per session scan C df32bb199940
termaway CLAUDE.md is an instructions file published in the GitHub repository alexkerber/termaway (5 stars, last pushed 1mo ago), licensed MIT. It adds 3,272 tokens to every session, about $0.0164 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
ios-swiftui-accessibility-techniques CLAUDE.md
Claude Code instructions for cvs-health/ios-swiftui-accessibility-techniques, covering project rules, copyright header (required), rules, swift files and markdown files.
AniShelf AGENTS.md
Instructions for samuelhe52/AniShelf, covering anishelf - developer notes, workflow, code style, testing and commits.
swift-architecture-skill CLAUDE.md
Instructions for efremidze/swift-architecture-skill, covering swift architecture skill, project structure, how the skill works and key conventions.
wolfpack AGENTS.md
AGENTS.md instructions for almogdepaz/wolfpack: This repo ships deep architectural context generated by EDC.
swift-architecture-skill AGENTS.md
Instructions for efremidze/swift-architecture-skill, covering agents guidelines for swift architecture skill, working with this repository, 1. understanding the skill, 2. modifying architecture playbooks and 3. testing and validation.
webspace_app CLAUDE.md
Claude Code instructions for theoden8/webspace_app, covering claude.md, style (output, code, commits), git, sandbox bootstrap and fvm — required (.fvmrc pins flutter 3.38.6).