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/hjertefolger/root_operator/claude-mdgit clone --depth 1 https://github.com/hjertefolger/Root_OperatorWhat 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 | $0.02325 | $0.02325 |
| Opus 5 | $0.01162 | $0.01162 |
| Sonnet 5 | $0.00465 | $0.00465 |
| Haiku 4.5 | $0.00232 | $0.00232 |
Grade A, and why
Root_Operator CLAUDE.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.
This is a copy
94% identical to Root_Operator AGENTS.md — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 231 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
Root Operator is a personal AI assistant for macOS powered by Claude Code channels. It combines chat, terminal access, identity-aware workspace bootstrapping, and secure remote access into a single desktop product.
Build & Development Commands
# Install dependencies (triggers automatic native rebuild)
npm install
# Start app in development mode with HMR (recommended)
npm run dev:app
# Start app without HMR (loads built files)
npm start
# Rebuild native modules (node-pty, keytar) after node/electron version changes
npm run rebuild
# Build for macOS (unsigned, for local development)
npm run build:unsigned
# Build for macOS (requires Apple Developer credentials)
npm run build
Development with HMR
The npm run dev:app command starts:
- Vite dev server for renderer on port 5174 (tray app HMR)
- Vite dev server for client on port 5175 (PWA client HMR)
- Electron loading from the dev servers
Changes to React components are reflected immediately:
src/renderer/- Tray app components (hot reload)src/client/- PWA client components (hot reload via proxy)
Architecture Overview
Process Architecture
Main Process (main.js):
- Electron main process that manages the app window, tray, and system integration
- HTTP server (port 22000) that serves PWA client and handles WebSocket connections
- Cloudflare tunnel manager that creates public URLs via
cloudflaredpackage - PTY (pseudoterminal) manager using
node-ptyfor shell process spawning - E2E encryption layer using ECDH key exchange + AES-256-GCM
- Secure credential storage via
keytar(macOS Keychain)
Renderer Process (src/renderer/):
- React + Tailwind + shadcn/ui components
- Entry point:
renderer.html(built toui/dist/renderer.html) - Main app:
src/renderer/App.jsx - Components in
src/renderer/components/(MainView, SettingsView, etc.) - Communicates with main process via IPC (see
preload.jsfor channel whitelist)
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.
- 2d ago First seen · 231 lines · 2,325 tokens per session scan A 6416a9939e4f
Root_Operator CLAUDE.md is an instructions file published in the GitHub repository hjertefolger/Root_Operator (9 stars, last pushed 3mo ago), licensed MIT. It adds 2,325 tokens to every session, about $0.0116 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to Root_Operator AGENTS.md, differing in 6 lines, and is treated as a copy.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.