What is TokenTracker CLAUDE.md?

A project instruction file for Token Tracker, a local application that records AI token use through a command-line tool, web dashboard, and desktop apps.

Use it when working on the tracker’s command-line interface, dashboard, local server, macOS app, Windows app, packaging, or deployment.

It explains the repository layout, build commands, and conventions so coding agents know where changes belong across its Node.js, React, macOS, and Windows parts.

How xiufengsun/TokenTracker configures Claude Code

About the project

Token Tracker is a local-first dashboard and desktop application that records AI token usage and costs across coding tools. It is for developers who want to monitor their coding-tool consumption, model usage, rate limits, and spending without relying on a cloud account.

xiufengsun/TokenTracker · 1,550 stars · on GitHub · tokentracker.cc

Reuse

Borrowing it

Nothing to install: this file belongs to xiufengsun/TokenTracker. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/xiufengsun/TokenTracker/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/xiufengsun/TokenTracker

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/xiufengsun/tokentracker/claude-md/github.svg)](https://agentmods.dev/instructions/xiufengsun/tokentracker/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/xiufengsun/tokentracker/claude-md"><img src="https://agentmods.dev/badge/instructions/xiufengsun/tokentracker/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/xiufengsun/tokentracker/claude-md"><img src="https://agentmods.dev/badge/instructions/xiufengsun/tokentracker/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,886 This file is loaded in full into every session.

When invoked 4,886 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What 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 5.1	$0.04886	$0.04886
Opus 5	$0.02443	$0.02443
Sonnet 5	$0.00977	$0.00977
Haiku 4.5	$0.00489	$0.00489

Measured 6d ago against content hash df7ce153fe03, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

TokenTracker 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 6d 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.

CLAUDE.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code working in this repository. Every line here is loaded into every conversation turn — keep it lean and current.

Project shape

Token Tracker is a local-first AI token usage tracker.

CLI (src/, CommonJS, Node ≥20) — entry bin/tracker.js → src/cli.js. serve runs a local HTTP server on :7680, sync parses logs into ~/.tokentracker/queue.jsonl.
Dashboard (dashboard/, React 18 + Vite 7 + TS strict + Tailwind) — built to dashboard/dist/, served by the CLI locally and by Vercel at www.tokentracker.cc.
macOS app (TokenTrackerBar/, Swift 5.9, XcodeGen) — menu bar + WidgetKit. EmbeddedServer/ bundles the CLI runtime + built dashboard so the .app is self-contained.
Windows app (TokenTrackerWin/, .NET 8 WinForms + WPF + WebView2) — system-tray counterpart of the macOS app. Launches the bundled CLI serve on a dynamic loopback port (avoids the DoSvc-held :7680), hosts the dashboard in WebView2, registers the tokentracker:// deep-link for OAuth. Built EmbeddedServer/ (Node + CLI + dashboard) is bundled by scripts/bundle-node.ps1 so the .exe is self-contained. Dashboard adaptations are gated behind isNativeWindowsApp() (dashboard/src/lib/native-bridge.js) so macOS/web paths are untouched.

Data flow: AI CLI runs → hook fires → rollout.js parses → queue.jsonl → local API → dashboard.

For the canonical list of supported providers, grep parse*Incremental in src/lib/rollout.js — the source of truth, not this file.

Frequently used commands

npm test                                  # node --test test/*.test.js  (209 files)
node --test test/<name>.test.js           # single test file
npm run ci:local                          # tests + validations + builds
npm run dashboard:dev                     # Vite dev server with local API mock (port 5173)
npm run dashboard:build                   # build to dashboard/dist/
npm run validate:copy                     # copy registry completeness
npm run validate:ui-hardcode              # no hardcoded UI strings
npm run validate:guardrails               # architecture guardrails
node bin/tracker.js serve --no-sync       # local dashboard server on :7680

Read the full file on GitHub · 183 lines

Changes

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.

6d ago Changed · +8 lines · +256 tokens per session df7ce153fe03
9d ago First seen · 175 lines · 4,630 tokens per session scan A 7cc5ea909446

Subscribe to this mod's changes

TokenTracker CLAUDE.md is an instructions file published in the GitHub repository xiufengsun/TokenTracker (1,550 stars, last pushed yesterday), licensed MIT. It adds 4,886 tokens to every session, about $0.0244 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code cli codex-cli cost-tracker cursor gemini-cli

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

TokenTracker: Instructions file for Claude Code