nateherkai

Token Dashboard — Data skill for Claude Code

Data community

See where Claude Code is burning tokens - turn raw JSONL transcripts into local cost analytics, hotspot views, and session-level usage insight.

How to install Token Dashboard

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

What Token Dashboard does

See where Claude Code is burning tokens - turn raw JSONL transcripts into local cost analytics, hotspot views, and session-level usage insight.

Alternatives in Data

Financial Services — Reference agents, skills, and data connectors for the financial-services workflows we see most — investment ba 34.5k ★
Claude Code Memory Setup — Up to 71.5x fewer tokens per session on Claude Code with Obsidian + Graphify 947 ★
Query Token Info — Search tokens and fetch metadata, real-time market data, and K-Line candlestick charts by keyword or contract 483 ★

README

Token Dashboard

A local dashboard that reads the JSONL transcripts Claude Code writes to `~/.claude/projects/` and turns them into per-prompt cost analytics, tool/file heatmaps, subagent attribution, cache analytics, project comparisons, and a rule-based tips engine.

**Everything runs locally.** No data leaves your machine — no telemetry, no API calls for your data, no login.

![Overview tab — totals and daily charts](docs/images/dashboard-overview-top.jpg)

![Overview tab — per-project, per-model, top tools, recent sessions](docs/images/dashboard-overview-bottom.jpg)

What this is useful for

Seeing which of your prompts are expensive (surprise: they usually involve large tool results).
Comparing token usage across projects you've worked on.
Spotting wasteful patterns — the same file read twenty times in a session, a tool call returning 80k tokens.
Understanding what a "cache hit" actually saves you.
If you're on Pro or Max, confirming you're getting your money's worth in API-equivalent dollars.

Prerequisites

Python 3.8 or newer — already installed on macOS and most Linux. On Windows: winget install Python.Python.3.12 or download from python.org.
Claude Code — installed and with at least one session run. The dashboard reads those sessions. If you just installed Claude Code and haven't used it yet, run at least one prompt first.
A web browser. Any modern one.

No `pip install`. No Node.js. No build step.

Quickstart

git clone https://github.com/nateherkai/token-dashboard.git
cd token-dashboard
python3 cli.py dashboard

On Windows, if `python3` isn't on your PATH, substitute `py -3` for `python3` in every command below.

The command:

Scans ~/.claude/projects/ (first run can take 20–60 seconds on a heavy user's machine).
Starts a local server at http://127.0.0.1:8080.
Opens your default browser to that URL.

Leave it running; it re-scans every 30 seconds and pushes updates live. Stop with `Ctrl+C`.