Borrowing it
Nothing to install: this file belongs to 48Nauts-Operator/xNaut. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/48Nauts-Operator/xNaut/main/CLAUDE.mdgit clone --depth 1 https://github.com/48Nauts-Operator/xNautWrote 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/48nauts-operator/xnaut/claude-md)<a href="https://agentmods.dev/instructions/48nauts-operator/xnaut/claude-md"><img src="https://agentmods.dev/badge/instructions/48nauts-operator/xnaut/claude-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.
<a href="https://agentmods.dev/instructions/48nauts-operator/xnaut/claude-md"><img src="https://agentmods.dev/badge/instructions/48nauts-operator/xnaut/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.06970 | $0.06970 |
| Opus 5.5 | $0.02788 | $0.02788 |
| Sonnet 5.5 | $0.01394 | $0.01394 |
| Haiku 4.5 | $0.00697 | $0.00697 |
Grade D, and why
xNaut CLAUDE.md scanned grade D with 2 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 24d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt-get install -y \ Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- Check key permissions: `chmod 600 ~/.ssh/id_rsa` How it starts
The opening of the file, as written. The whole thing — 812 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 Overview
xNAUT is an AI-powered native terminal application built with Tauri v2, combining Rust backend performance with a modern web-based frontend. Originally converted from "Naiterm" (Node.js terminal app) to a native macOS application for better performance and smaller binary size (~5-10MB vs Electron's ~500MB).
Key Features
- Multiple PTY sessions with tab management
- SSH connection support with config file integration
- AI chat integration (Anthropic, OpenAI, OpenRouter, Perplexity)
- Workflow recording and playback
- Smart triggers and notifications
- Session sharing capabilities
Current Status
✅ Build-ready with critical ACL permissions fix applied ⚠️ Terminal functionality needs verification after ACL fix
Grep before you call a window.* global
An undefined global in JavaScript is a silent no-op, not a crash. It survives
node --check, a clean build, a green test suite and a code read — and then the
feature just quietly does nothing, forever, with no error to notice.
Hit for real 2026-08-08: the roster panel called window.xnautActiveProjectKey,
which had never existed. The expression short-circuited to null, so the
per-project scope silently fell back to global. Nothing errored.
The trap has a second floor. Exporting the missing global as a function while
the call site treats it as a value is worse than the original bug: a function
object is truthy, so it gets used as data — in that case as a localStorage key,
writing settings to xnaut-agent-roster:function () { return activeProjectId….
Still no error.
So: before calling window.something, grep for where it is assigned. If it
does not exist, export it properly and fix the call site to match its shape. This
is the same failure class as the gate-path bug the same day — passes every
automated check, silently wrong — and it is worth the ten seconds every time.
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.
- 24d ago First seen · 812 lines · 6,970 tokens per session scan D d3b4c2989482
xNaut CLAUDE.md is an instructions file published in the GitHub repository 48Nauts-Operator/xNaut (6 stars, last pushed 15d ago), licensed MIT. It adds 6,970 tokens to every session, about $0.0279 per session on Opus 5.5. A static security scan graded it D with 2 findings (asks for root, reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-04.
Other instructions, from other repositories
vscode buildNext.instructions.md
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.