FreePeak

Token Lens — Data skill for Claude Code

Data community

Local-only dashboard for AI coding sessions.

How to install Token Lens

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

What Token Lens does

Local-only dashboard for AI coding sessions. Track turns, tokens, and cost across Cursor, Claude Code, and OpenCode. All data stays on your machine.

Alternatives in Data

Claude Code Memory Setup — Up to 71.5x fewer tokens per session on Claude Code with Obsidian + Graphify 947 ★
Memex — Open-source, local-first AI journal app for iOS and Android 697 ★
Token Dashboard — See where Claude Code is burning tokens - turn raw JSONL transcripts into local cost analytics, hotspot views 669 ★

README

Token Lens - Local AI Coding Session Dashboard

See exactly where your AI coding budget goes — turns, tokens, and cost per session.

Quick start · Features · Dashboard · CLI · Supported tools · Contributing

MIT GitHub stars Latest release

What is Token Lens?

**Token Lens** is a local-first dashboard that turns your AI coding sessions into transparent cost and usage data. It reads from Cursor's local state database, captures live hooks, and estimates spending based on each model's public API pricing.

No data leaves your machine. Nothing is uploaded. The privacy guarantee is baked into the architecture.

If you use AI coding tools daily, you've probably asked: *"How many tokens did that session burn?"* or *"Which model is driving up my bill?"* Token Lens answers those questions — for free, offline, and instantly.

Quick start

# Requires Bun ≥1.0 — install: https://bun.sh
git clone https://github.com/FreePeak/token-lens.git
cd token-lens

# Install dependencies
bun install
cd dashboard && bun install && cd ..

# Import historical sessions from Cursor
bun run back