Dicklesworthstone

Rano — AI skill for Claude Code

AI community

Network observer that tracks outbound connections from AI CLI processes (Claude Code, Codex, Gemini), attributing sockets to providers in real time with SQLite logging.

How to install Rano

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Dicklesworthstone/rano and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Rano does

Network observer that tracks outbound connections from AI CLI processes (Claude Code, Codex, Gemini), attributing sockets to providers in real time with SQLite logging.

Alternatives in AI

Manifest — Real-time cost observability for OpenClaw agents — track tokens, costs, messages, and model usage 4.1k ★
Sentrux — Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improveme 2.9k ★
CodeIsland — Real-time AI coding agent status panel in your MacBook notch — live status, approvals & replies for 13 AI tool 2.3k ★

README

rano

[![Release](https://img.shields.io/github/v/release/Dicklesworthstone/rano?sort=semver)](https://github.com/Dicklesworthstone/rano/releases)

rano is a **network observer for AI CLI processes** that tracks outbound connections from Claude Code, Codex CLI, Gemini CLI, and their descendants—live in your terminal and durably in SQLite.

Quick Install

curl -fsSL https://raw.githubusercontent.com/Dicklesworthstone/rano/main/install.sh | bash

TL;DR

**The Problem**: AI CLI tools spawn subprocesses and open sockets you can’t easily attribute back to a provider or process in real time.

**The Solution**: rano polls `/proc`, maps sockets to PIDs, and prints connection events with provider tags while logging a complete history to SQLite.

Why Use rano?

Feature	What It Does
Provider-aware	Tags traffic as `anthropic`, `openai`, `google`, or `unknown`.
Descendant-aware	Follows child processes automatically.
Live stats	In-terminal summaries with top IPs/domains and provider totals.
SQLite logging	Queryable history with built-in aggregate views.
Flexible output	Pretty or JSON output + optional file logging.

Quick Example

# Observe default AI CLIs (claude/codex/gemini)
./rano

# Narrow to Codex + log JSON
rano --pattern codex --json --log-file /tmp/rano.log

# Run with per-run log files
rano --log-dir /tmp/rano-logs --log-format json

# Track a specific PID (no descendants)
rano --pid 1234 --no-descendants

# Emit a single poll and exit
rano --once

# View SQLite aggregates
sqlite3 observer.sqlite "select * from provider_counts;"