infenia

Claudon — Data skill for Claude Code

Data community

Local Claude Code analytics dashboard – see time, cost, bottlenecks & thinking.

How to install Claudon

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

What Claudon does

Local Claude Code analytics dashboard – see time, cost, bottlenecks & thinking. 100% private, MIT, one command.

Alternatives in Data

Private GPT — Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more 57.5k ★
Financial Services — Reference agents, skills, and data connectors for the financial-services workflows we see most — investment ba 34.5k ★
Agentsview — Local-first session intelligence and analytics for coding agents, supporting Claude Code, Codex, and 14 other 824 ★

README

Claudon

**See where your Claude Code time and money actually go.**

One command turns your session logs into an interactive HTML dashboard.
100% local · zero dependencies · nothing leaves your machine.

[![CI](https://github.com/infenia/claudon/actions/workflows/ci.yml/badge.svg)](https://github.com/infenia/claudon/actions/workflows/ci.yml) [![PyPI](https://img.shields.io/pypi/v/claudon?label=PyPI)](https://pypi.org/project/claudon/) [![npm](https://img.shields.io/npm/v/@infenia/claudon)](https://www.npmjs.com/package/@infenia/claudon) [![Python](https://img.shields.io/pypi/pyversions/claudon?label=Python)](https://pypi.org/project/claudon/) [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)

uvx claudon --open

Claudon dashboard tour: overview, tasks, tools, models and bottlenecks

Redacted sample. Your own sessions stay on your machine.

[Quick start](#quick-start) · [In the browser](#in-the-browser-no-install) · [Usage](#usage) · [Privacy](#privacy) · [Contributing](#contributing)

Why Claudon?

Claude Code is fast until it isn't. Which turn burned ten minutes? Was it the model, a slow tool, or you being away? Did a failing tool call loop? What did the session really cost?

The answers are already in `~/.claude`. Claudon reads them and shows you:


Where time went	model vs. tools vs. permission waits vs. idle, per task, turn and subagent
What it cost	token usage × list prices per model generation (override with `--pricing`)
What went wrong	automatic detection of tool failures, slow turns and retry loops
How hard it thought	thinking time vs. thinking tokens
Safe to share	`--redact` strips prompts, paths, commands an